How can I get the exact torch operator of each node?

torch.compile FX (Functional Transformations)
1

Dear experts,

I am trying to iterate through the nodes in a model with an interpreter pattern and find the exact operators used. However, not sure how I can do this. For example, if I put the below print statement for each node:

print(f"{n}, {n.op}, {n.target}")

where n is a node, I get something like below:

bert_pooler_activation, call_module, bert.pooler.activation

Here, bert.pooler.activation is in fact torch.nn.Tanh, but that information is not shown at all. Is there a way for me to figure out that it is a Tanh?
I tried this and that but could not figure it out.

Any suggestions or pointers will be highly appreciated!
Thank you