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

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

Neuron 1450 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: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0004

Data Index: 85501 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0434. Min Act: -0.0003

Data Index: 389076 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1262244 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0429. Min Act: -0.0003

Data Index: 42711 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0433. Min Act: -0.0003

Data Index: 357028 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0426. Min Act: -0.0003

Data Index: 936558 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0420. Min Act: -0.0003

Data Index: 871049 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0421. Min Act: -0.0003

Data Index: 75382 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0417. Min Act: -0.0003

Data Index: 626249 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0425. Min Act: -0.0003

Data Index: 81787 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0405. Min Act: -0.0003

Data Index: 615573 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0402. Min Act: -0.0003

Data Index: 357371 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0404. Min Act: -0.0004

Data Index: 424923 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0408. Min Act: -0.0003

Data Index: 786227 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0397. Min Act: -0.0003

Data Index: 878215 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0397. Min Act: -0.0003

Data Index: 939620 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0382. Min Act: -0.0003

Data Index: 371976 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0380. Min Act: -0.0003

Data Index: 132369 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0386. Min Act: -0.0002

Data Index: 596922 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1145507 (C4 (Web Text))

Max Activating Token Index: 400