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

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

Neuron 3397 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: 0.0367. Min Range: -0.0367

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1612942 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0314. Min Act: -0.0002

Data Index: 471888 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0002

Data Index: 211327 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0274. Min Act: -0.0002

Data Index: 359669 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0246. Min Act: -0.0002

Data Index: 374970 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0282. Min Act: -0.0002

Data Index: 486557 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0242. Min Act: -0.0002

Data Index: 697510 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0238. Min Act: -0.0002

Data Index: 178878 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0268. Min Act: -0.0002

Data Index: 96879 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1261051 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0286. Min Act: -0.0002

Data Index: 550976 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0264. Min Act: -0.0002

Data Index: 394553 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0238. Min Act: -0.0002

Data Index: 613827 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0258. Min Act: -0.0002

Data Index: 108186 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0216. Min Act: -0.0002

Data Index: 362593 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0242. Min Act: -0.0002

Data Index: 336412 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0236. Min Act: -0.0002

Data Index: 256210 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0232. Min Act: -0.0002

Data Index: 849703 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0252. Min Act: -0.0002

Data Index: 923039 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1175921 (C4 (Web Text))

Max Activating Token Index: 361