Upgrading transformer_lens to 1.4.0 caused
`HookedTransformer.process_weights_()` to no longer accept
the keyword arg `move_state_dict_to_device`

However, I'm not sure if this was important in the first place.
If any issues come up, move the state dict to device manually in
`ZanjHookedTransformer._load_state_dict_wrapper()` where all this
was happening in the first place

since we removed tokenizer stuff from the dataset

the `eval_model.ipynb` notebook has a function `testdata_plot_predicted_path`
which was using `model.zanj_model_config` to get the tokenizer, an attribute
missing from the `RandomBaseline` class since it only inherits from `HookedTransformer`

to fix this:

- `ZanjHookedTransformer` now has a `config` property which just
  accesses the `zanj_model_config` used by the parent `ConfiguredModel`
- `testdata_plot_predicted_path` now uses `model.config` everywhere