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

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

Neuron 588 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: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0006

Data Index: 705798 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1304711 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1370624 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0331. Min Act: -0.0006

Data Index: 1095252 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1224489 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0331. Min Act: -0.0006

Data Index: 11710 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0321. Min Act: -0.0006

Data Index: 860224 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1266527 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0318. Min Act: -0.0006

Data Index: 169392 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0310. Min Act: -0.0006

Data Index: 488124 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0319. Min Act: -0.0006

Data Index: 198967 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0307. Min Act: -0.0006

Data Index: 378241 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0317. Min Act: -0.0006

Data Index: 493675 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0316. Min Act: -0.0006

Data Index: 760071 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0316. Min Act: -0.0006

Data Index: 340336 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0285. Min Act: -0.0006

Data Index: 413641 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1449158 (Python Code)

Max Activating Token Index: 890

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0309. Min Act: -0.0006

Data Index: 877745 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0291. Min Act: -0.0006

Data Index: 403537 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0294. Min Act: -0.0005

Data Index: 308638 (C4 (Web Text))

Max Activating Token Index: 938