A new article was just posted, co-authored by @vrodriguezf! 
We added in a show_at function to the interpretation class to take a look at individual items, as well as a __getitem__ to quickly grab the stored inputs, preds, targets, decoded outputs, and losses at particular indices you may be interested in (such as those returned by top_losses)
Article: https://walkwithfastai.com/interp