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

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

Neuron 2353 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0002

Data Index: 117613 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0297. Min Act: -0.0002

Data Index: 781278 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1052244 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1197026 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0280. Min Act: -0.0002

Data Index: 563778 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1131759 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1071250 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0274. Min Act: -0.0002

Data Index: 595357 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0273. Min Act: -0.0002

Data Index: 184204 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0272. Min Act: -0.0002

Data Index: 683806 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1266603 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0270. Min Act: -0.0002

Data Index: 582267 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0002

Data Index: 318465 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0002

Data Index: 425007 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0002

Data Index: 480141 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0259. Min Act: -0.0002

Data Index: 988927 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0263. Min Act: -0.0002

Data Index: 609412 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0263. Min Act: -0.0002

Data Index: 998106 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0268. Min Act: -0.0002

Data Index: 420454 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0002

Data Index: 643649 (C4 (Web Text))

Max Activating Token Index: 197