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

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

Neuron 4406 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: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0003

Data Index: 192950 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1183940 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0218. Min Act: -0.0003

Data Index: 660481 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0236. Min Act: -0.0003

Data Index: 165078 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0216. Min Act: -0.0003

Data Index: 313051 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0208. Min Act: -0.0003

Data Index: 639907 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0208. Min Act: -0.0002

Data Index: 469088 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1278911 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1029907 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0203. Min Act: -0.0003

Data Index: 759093 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0205. Min Act: -0.0003

Data Index: 881299 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1139088 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0195. Min Act: -0.0002

Data Index: 360464 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1154254 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0176. Min Act: -0.0002

Data Index: 541749 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0197. Min Act: -0.0002

Data Index: 709531 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1182138 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0201. Min Act: -0.0002

Data Index: 133152 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0189. Min Act: -0.0003

Data Index: 612896 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1142732 (C4 (Web Text))

Max Activating Token Index: 993