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

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

Neuron 1396 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: 0.0360. Min Range: -0.0360

Max Act: 0.0354. Min Act: -0.0002

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1181756 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0220. Min Act: -0.0002

Data Index: 335676 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1341829 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0232. Min Act: -0.0002

Data Index: 101565 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0263. Min Act: -0.0002

Data Index: 936640 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0207. Min Act: -0.0002

Data Index: 685527 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1177940 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1280386 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0204. Min Act: -0.0002

Data Index: 4730 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0202. Min Act: -0.0003

Data Index: 212151 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1091692 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1259741 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1431651 (Python Code)

Max Activating Token Index: 452

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0193. Min Act: -0.0002

Data Index: 126247 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0233. Min Act: -0.0002

Data Index: 690565 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0208. Min Act: -0.0002

Data Index: 531536 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0203. Min Act: -0.0002

Data Index: 643099 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0173. Min Act: -0.0002

Data Index: 138908 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1229550 (C4 (Web Text))

Max Activating Token Index: 553