Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2652 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1288234 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0251. Min Act: -0.0003

Data Index: 65538 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0003

Data Index: 778760 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0250. Min Act: -0.0003

Data Index: 296983 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0230. Min Act: -0.0003

Data Index: 19657 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0241. Min Act: -0.0003

Data Index: 647316 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0240. Min Act: -0.0003

Data Index: 650633 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0227. Min Act: -0.0003

Data Index: 887220 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0223. Min Act: -0.0003

Data Index: 502375 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0234. Min Act: -0.0003

Data Index: 675264 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0243. Min Act: -0.0003

Data Index: 181648 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0234. Min Act: -0.0003

Data Index: 435601 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0003

Data Index: 658492 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1177240 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0216. Min Act: -0.0003

Data Index: 439392 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1033858 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0224. Min Act: -0.0003

Data Index: 987848 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0222. Min Act: -0.0003

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0229. Min Act: -0.0003

Data Index: 632159 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0215. Min Act: -0.0003

Data Index: 426593 (C4 (Web Text))

Max Activating Token Index: 1018