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

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

Neuron 980 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: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1151579 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1148975 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0221. Min Act: -0.0003

Data Index: 59683 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0228. Min Act: -0.0004

Data Index: 791374 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0197. Min Act: -0.0003

Data Index: 995927 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0199. Min Act: -0.0003

Data Index: 357325 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0194. Min Act: -0.0003

Data Index: 377722 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0188. Min Act: -0.0003

Data Index: 994566 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0185. Min Act: -0.0003

Data Index: 39199 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0175. Min Act: -0.0003

Data Index: 294150 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0183. Min Act: -0.0003

Data Index: 92911 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1231133 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1315072 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1362873 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1303675 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1303607 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1629295 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0170. Min Act: -0.0003

Data Index: 689767 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0181. Min Act: -0.0004

Data Index: 399585 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0177. Min Act: -0.0003

Data Index: 947294 (C4 (Web Text))

Max Activating Token Index: 85