Fix the insert_guard for norm decomposation (#19646)
Summary:
move the insert_guard all the way up to the beginning of the decomposation, this will fix the case that we lose insert_point context after decomposeCommonNormalization and we still need to modify the graph.
fixes #19502
Pull Request resolved: https://github.com/pytorch/pytorch/pull/19646
Differential Revision: D15058040
Pulled By: wanchaol
fbshipit-source-id: ebdbf8623ebfe4556c461e1b650e94b905791adb