gradient-based saliency maps to support different activations

class GuidedBackpropGrad(VanillaGrad):
   

    def __call__(self, x: torch.Tensor, index: torch.Tensor | int | None = None, **kwargs) -> torch.Tensor:
        with replace_modules_temp(self.model, "relu", _GradReLU(), strict_match=False):
            return super().__call__(x, index, **kwargs)

I think the method tries to look for "relu" layers and replace it with a grad-hooked customised one. This assumingly might not work with other activation functions. this is a feature request to support different activation functions, SiLU for instance.

Originally posted by @trinhdhk in https://github.com/Project-MONAI/MONAI/discussions/6012#discussioncomment-5047022

Start with GuidedBackpropGrad.call, the temporary replace_modules_temp call, and the _GradReLU implementation shown in the issue. Determine how activation replacement currently works, then define support for SiLU and other activation functions; done means gradient-based saliency maps work with those activations and the relevant behavior is covered by tests.