Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3529 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1045818 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1421. Min Act: -0.0001

Data Index: 748871 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1210388 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1368. Min Act: -0.0001

Data Index: 309650 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1031280 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1310. Min Act: -0.0000

Data Index: 962356 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1259. Min Act: -0.0001

Data Index: 600371 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1290. Min Act: -0.0001

Data Index: 19025 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1300. Min Act: -0.0001

Data Index: 789863 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1325. Min Act: -0.0001

Data Index: 566784 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1265015 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1353. Min Act: -0.0001

Data Index: 419854 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1300. Min Act: -0.0001

Data Index: 196386 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1315. Min Act: -0.0001

Data Index: 709583 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1175016 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1283. Min Act: -0.0001

Data Index: 89425 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1281. Min Act: -0.0001

Data Index: 32370 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1072. Min Act: -0.0001

Data Index: 786465 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1032089 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1039. Min Act: -0.0000

Data Index: 804364 (C4 (Web Text))

Max Activating Token Index: 12