The curious feature of Tocharian A & B is that they are centum languages, otherwise found in Europe (like Latin, Greek, Celtic, and Germanic) whereas other eastern Indo-European languages are usually satem languages (such as Slavic, Iranian, Sanskrit). The difference between the two groups is that the centum languages consistently have a "k" sound (which becomes "h" in Germanic) where the satem languages have an "s" sound. (Centum is Latin for 100, satem is Avestan for 100.)
So it looks like the speakers of Tocharian A and B had migrated from much further west. They were a separate branch of the Indo-European family, not directly connected to the Celts.
Professor Victor Mair, in his book, The Tarim Mummies, states that the Tocharian language, of all the Indo-European languages, is closest related to ancient Celtic.
Professor Elizabeth Barber, in her book, The Mummies Of Urumchi, makes another connection to the Celtics with the textiles found on/with the Tarim Mummies to the Celtic fabrics found at Hallstadt.
Both those are excellent books, BTW.
Yes. I think there was no evidence that directly connected the Tocharian languages to the earliest of the Caucasian mummies. BTW, the Mongoloid skeletons/mummies only began appearing in that region around 100-200BC.
"Narain (an Indian Archaeologist) argues that once one accepts the equation Tocharian = Yuezhi, then one is forced to follow both the Chinese historical record sources and the geographical reference of their (the Caucasian mummies) first cited historical location (Gansu) to the conclusion that they have been there 'from times immemorial'. Narain infers that they had been there at least since the Qijia culture c. 2000BC and probably even earlier in the Yangshao culture of the Neolithic. This would render the Tocharians as virtually native to Gansu (and earlier than the putative spread of the Neolithic to Xinjiang) and Narain goes so far as to argue that the Indo-Europeans themselves originally dispersed from this area westwards."