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

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

Neuron 1643 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: 0.0391. Min Range: -0.0391

Max Act: 0.0376. Min Act: -0.0006

Data Index: 348902 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1180323 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0368. Min Act: -0.0006

Data Index: 370297 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0367. Min Act: -0.0005

Data Index: 474141 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0378. Min Act: -0.0006

Data Index: 547853 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0370. Min Act: -0.0006

Data Index: 464300 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0366. Min Act: -0.0005

Data Index: 487319 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0355. Min Act: -0.0006

Data Index: 599082 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0360. Min Act: -0.0006

Data Index: 455869 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0351. Min Act: -0.0006

Data Index: 1094114 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0350. Min Act: -0.0006

Data Index: 160211 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0350. Min Act: -0.0006

Data Index: 908009 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0341. Min Act: -0.0006

Data Index: 592547 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0348. Min Act: -0.0006

Data Index: 303625 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0362. Min Act: -0.0006

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0340. Min Act: -0.0005

Data Index: 439555 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0352. Min Act: -0.0006

Data Index: 289361 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0351. Min Act: -0.0006

Data Index: 227028 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0336. Min Act: -0.0006

Data Index: 324568 (C4 (Web Text))

Max Activating Token Index: 288