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

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

Neuron 37 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0342. Min Act: -0.0006

Data Index: 717870 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1268235 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0328. Min Act: -0.0006

Data Index: 391412 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0326. Min Act: -0.0006

Data Index: 421631 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0326. Min Act: -0.0006

Data Index: 587323 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0328. Min Act: -0.0006

Data Index: 574005 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1045497 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0319. Min Act: -0.0006

Data Index: 726362 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0323. Min Act: -0.0006

Data Index: 77107 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1048329 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0314. Min Act: -0.0006

Data Index: 157473 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0300. Min Act: -0.0006

Data Index: 820288 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0294. Min Act: -0.0006

Data Index: 204706 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0286. Min Act: -0.0006

Data Index: 39130 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0305. Min Act: -0.0006

Data Index: 539280 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0282. Min Act: -0.0006

Data Index: 256055 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1298873 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1194499 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0280. Min Act: -0.0006

Data Index: 978867 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0286. Min Act: -0.0006

Data Index: 656681 (C4 (Web Text))

Max Activating Token Index: 851