Dropout in LeakyParallel

[LuposX]

Does the dropout parameter in LeakyParallel do anything? From experimentation, even setting the parameter to 1, the model still learns.

The PyTorch RNN documentation, on which LeakyParallel is based, says:

dropout – If non-zero, introduces a Dropout layer on the outputs of each RNN layer except the last layer, with dropout probability equal to dropout. Default: 0

Is the dropout parameter of LeakyParallel ineffective because it only consists of one RNN layer, which is the output layer, and thus the parameter has no effect?