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

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

Neuron 3065 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: 0.4476. Min Range: -0.4476

Max Act: 0.4476. Min Act: -0.0002

Data Index: 1366694 (Python Code)

Max Activating Token Index: 425

Text #1

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3526. Min Act: -0.0002

Data Index: 614960 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3080. Min Act: -0.0002

Data Index: 627155 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3245. Min Act: -0.0002

Data Index: 145037 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3063. Min Act: -0.0002

Data Index: 1575391 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3377. Min Act: -0.0002

Data Index: 66291 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3318. Min Act: -0.0002

Data Index: 82607 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3282. Min Act: -0.0002

Data Index: 860991 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2808. Min Act: -0.0002

Data Index: 1478177 (Python Code)

Max Activating Token Index: 917

Text #9

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3585. Min Act: -0.0002

Data Index: 1253857 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3089. Min Act: -0.0002

Data Index: 1130443 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3236. Min Act: -0.0002

Data Index: 1156564 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2697. Min Act: -0.0003

Data Index: 1335675 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3169. Min Act: -0.0002

Data Index: 756975 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2481. Min Act: -0.0002

Data Index: 169120 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3133. Min Act: -0.0002

Data Index: 694579 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2818. Min Act: -0.0002

Data Index: 1032989 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3175. Min Act: -0.0002

Data Index: 294502 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2803. Min Act: -0.0002

Data Index: 722297 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3065. Min Act: -0.0002

Data Index: 749190 (C4 (Web Text))

Max Activating Token Index: 767