[Doc] Fix a typo in the tutorial for Neighbor Sampling (#2935)

Fix a typo in the tutorial for "Introduction of Neighbor Sampling for GNN Training".
Co-authored-by: Quan (Andy) Gan <coin2028@hotmail.com>

tutorials/large/L0_neighbor_sampling_overview.py

@@ -78,7 +78,7 @@ By the end of this tutorial, you will be able to
 #
 # Neighbor sampling addresses this issue by selecting a subset of the
 # neighbors to perform aggregation. For instance, to compute
-# :math:`\boldsymbol{h}_8^{(2)}`, you can choose two of the neighbors
+# :math:`\boldsymbol{h}_5^{(2)}`, you can choose two of the neighbors
 # instead of all of them to aggregate, as in the following animation:
 #
 # |image2|