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

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

Neuron 351 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: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0002

Data Index: 18925 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0414. Min Act: -0.0002

Data Index: 873024 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0395. Min Act: -0.0002

Data Index: 798450 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1021162 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1258461 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1180714 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0349. Min Act: -0.0002

Data Index: 749970 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0341. Min Act: -0.0002

Data Index: 317980 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0336. Min Act: -0.0002

Data Index: 570124 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0341. Min Act: -0.0002

Data Index: 348622 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0333. Min Act: -0.0002

Data Index: 359873 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1207982 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1168329 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0329. Min Act: -0.0002

Data Index: 912688 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0330. Min Act: -0.0002

Data Index: 564399 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0327. Min Act: -0.0002

Data Index: 701590 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0313. Min Act: -0.0002

Data Index: 94210 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1107336 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1313819 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0323. Min Act: -0.0002

Data Index: 583316 (C4 (Web Text))

Max Activating Token Index: 763