Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3319 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.8720. Min Act: -0.0002

Data Index: 380187 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7528. Min Act: -0.0002

Data Index: 485588 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7507. Min Act: -0.0002

Data Index: 59748 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7372. Min Act: -0.0002

Data Index: 1172978 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7273. Min Act: -0.0002

Data Index: 1093196 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7397. Min Act: -0.0002

Data Index: 1280488 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7559. Min Act: -0.0002

Data Index: 390083 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7433. Min Act: -0.0002

Data Index: 544772 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7446. Min Act: -0.0002

Data Index: 54810 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7293. Min Act: -0.0002

Data Index: 194349 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7235. Min Act: -0.0002

Data Index: 613958 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7071. Min Act: -0.0002

Data Index: 762791 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6399. Min Act: -0.0002

Data Index: 835800 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7032. Min Act: -0.0002

Data Index: 1230727 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6803. Min Act: -0.0002

Data Index: 919806 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6408. Min Act: -0.0002

Data Index: 955368 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6687. Min Act: -0.0002

Data Index: 485500 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6803. Min Act: -0.0002

Data Index: 232576 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6374. Min Act: -0.0002

Data Index: 1230092 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5701. Min Act: -0.0002

Data Index: 410938 (C4 (Web Text))

Max Activating Token Index: 271