Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1636 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0911. Min Act: -0.0001

Data Index: 880760 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1050405 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0856. Min Act: -0.0001

Data Index: 265474 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0834. Min Act: -0.0002

Data Index: 353246 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0803. Min Act: -0.0001

Data Index: 617207 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1205947 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0811. Min Act: -0.0002

Data Index: 528903 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0805. Min Act: -0.0002

Data Index: 23980 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1113244 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0797. Min Act: -0.0002

Data Index: 359533 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1150624 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0819. Min Act: -0.0002

Data Index: 584849 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1042194 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0807. Min Act: -0.0002

Data Index: 770373 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0776. Min Act: -0.0001

Data Index: 976155 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1209473 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1202762 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0777. Min Act: -0.0001

Data Index: 604577 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1219814 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0758. Min Act: -0.0002

Data Index: 329295 (C4 (Web Text))

Max Activating Token Index: 284