Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3420 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0002

Data Index: 894901 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0420. Min Act: -0.0002

Data Index: 402744 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1225312 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0309. Min Act: -0.0002

Data Index: 339570 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1122309 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0315. Min Act: -0.0002

Data Index: 727700 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1163143 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0297. Min Act: -0.0002

Data Index: 931451 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1200216 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1049459 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1071226 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0288. Min Act: -0.0002

Data Index: 290314 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1071680 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0301. Min Act: -0.0002

Data Index: 500523 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0289. Min Act: -0.0002

Data Index: 860017 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0274. Min Act: -0.0002

Data Index: 363939 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1283995 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0259. Min Act: -0.0002

Data Index: 724421 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0275. Min Act: -0.0002

Data Index: 184903 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0264. Min Act: -0.0002

Data Index: 181571 (C4 (Web Text))

Max Activating Token Index: 621