Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1718 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1171010 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0272. Min Act: -0.0003

Data Index: 380353 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0240. Min Act: -0.0004

Data Index: 699670 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1053756 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0243. Min Act: -0.0004

Data Index: 723398 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0248. Min Act: -0.0003

Data Index: 222096 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0243. Min Act: -0.0004

Data Index: 105644 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1321039 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0241. Min Act: -0.0003

Data Index: 97404 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0235. Min Act: -0.0003

Data Index: 532417 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0236. Min Act: -0.0003

Data Index: 427679 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0232. Min Act: -0.0003

Data Index: 215504 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1398008 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0225. Min Act: -0.0002

Data Index: 296756 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0237. Min Act: -0.0004

Data Index: 852222 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1264132 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0228. Min Act: -0.0003

Data Index: 478099 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0231. Min Act: -0.0003

Data Index: 982418 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1046327 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0223. Min Act: -0.0003

Data Index: 848687 (C4 (Web Text))

Max Activating Token Index: 571