At the very end of the IMDB review classification notebook (https://github.com/fastai/course-v3/blob/master/nbs/dl1/lesson3-imdb.ipynb) we gut check the model by passing an example review to the model:
learn.predict("I really loved that movie, it was awesome!")
The output looks correct, but is the text being processed to add xxbos
and other tokens like that? Is there a quick way to show what the processed text looks like? Would that be done with the learner or DataBunch?