Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 658 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0002

Data Index: 922831 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0238. Min Act: -0.0001

Data Index: 898476 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0232. Min Act: -0.0002

Data Index: 406297 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0228. Min Act: -0.0002

Data Index: 82069 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0002

Data Index: 112624 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1267511 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0002

Data Index: 8286 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0197. Min Act: -0.0002

Data Index: 777173 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0207. Min Act: -0.0002

Data Index: 394745 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0216. Min Act: -0.0002

Data Index: 309693 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0213. Min Act: -0.0002

Data Index: 531791 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1164069 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0197. Min Act: -0.0002

Data Index: 272792 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0197. Min Act: -0.0002

Data Index: 969517 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0189. Min Act: -0.0002

Data Index: 607491 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0196. Min Act: -0.0002

Data Index: 854754 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0198. Min Act: -0.0002

Data Index: 787420 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1283091 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0180. Min Act: -0.0002

Data Index: 176384 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0185. Min Act: -0.0002

Data Index: 638544 (C4 (Web Text))

Max Activating Token Index: 518