This is true but you have to also consider the autoregressive component. In your example, it's 50 steps per iteration of the model, where the model is executed once for each token in the output.
So practically speaking it's a bit more complicated to calculate how much the model can "think". Of course once a token is output it is committed to that (in the most basic scenario), but that doesn't mean it is not still "thinking" as it produces subsequent tokens.
> perhaps a notepad
Exactly, the context and previously output tokens can be considered such a notepad since they are input for the next steps of the model.