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

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

Neuron 4292 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0272. Min Act: -0.0002

Data Index: 725759 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0003

Data Index: 772205 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0002

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0230. Min Act: -0.0002

Data Index: 960199 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0206. Min Act: -0.0002

Data Index: 779936 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0205. Min Act: -0.0003

Data Index: 940221 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1262628 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0190. Min Act: -0.0002

Data Index: 305544 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1138893 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0179. Min Act: -0.0003

Data Index: 278000 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0173. Min Act: -0.0002

Data Index: 5111 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0170. Min Act: -0.0002

Data Index: 137232 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1261311 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1269338 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0167. Min Act: -0.0003

Data Index: 295786 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0163. Min Act: -0.0003

Data Index: 597507 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0166. Min Act: -0.0002

Data Index: 764315 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0163. Min Act: -0.0002

Data Index: 166954 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1230954 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1041542 (C4 (Web Text))

Max Activating Token Index: 368