Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0003

Data Index: 508056 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1215612 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0221. Min Act: -0.0003

Data Index: 500596 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0222. Min Act: -0.0003

Data Index: 127103 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1215041 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0197. Min Act: -0.0003

Data Index: 741255 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0203. Min Act: -0.0003

Data Index: 648574 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0200. Min Act: -0.0003

Data Index: 663861 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1070777 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0186. Min Act: -0.0003

Data Index: 781731 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1339502 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0178. Min Act: -0.0003

Data Index: 997139 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1112998 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1281613 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0168. Min Act: -0.0003

Data Index: 468490 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0175. Min Act: -0.0003

Data Index: 511939 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1296984 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1307167 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0180. Min Act: -0.0003

Data Index: 611438 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0183. Min Act: -0.0003

Data Index: 181080 (C4 (Web Text))

Max Activating Token Index: 376