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

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

Neuron 1539 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: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1313876 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1333687 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0405. Min Act: -0.0002

Data Index: 387883 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0386. Min Act: -0.0003

Data Index: 642017 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0383. Min Act: -0.0003

Data Index: 71663 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0357. Min Act: -0.0002

Data Index: 226771 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1002193 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0369. Min Act: -0.0003

Data Index: 556589 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0378. Min Act: -0.0003

Data Index: 785703 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1245812 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0377. Min Act: -0.0003

Data Index: 224749 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1256980 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0366. Min Act: -0.0002

Data Index: 536768 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0379. Min Act: -0.0002

Data Index: 795025 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1284786 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0356. Min Act: -0.0002

Data Index: 834361 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0367. Min Act: -0.0003

Data Index: 325758 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1043430 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1177527 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0363. Min Act: -0.0002

Data Index: 979330 (C4 (Web Text))

Max Activating Token Index: 890