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

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

Neuron 1887 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: 0.0459. Min Range: -0.0459

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1246558 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1483932 (Python Code)

Max Activating Token Index: 83

Text #2

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1436632 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1377797 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1410124 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1377900 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1509843 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1564247 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1468053 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1444461 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1580708 (Python Code)

Max Activating Token Index: 286

Text #11

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1458220 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1420502 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1524709 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1540380 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1612808 (Python Code)

Max Activating Token Index: 283

Text #16

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1499353 (Python Code)

Max Activating Token Index: 580

Text #17

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1547384 (Python Code)

Max Activating Token Index: 643

Text #18

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1630119 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1570292 (Python Code)

Max Activating Token Index: 278