Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4497 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1780. Min Act: -0.0000

Data Index: 814610 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1501. Min Act: -0.0000

Data Index: 613883 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1438. Min Act: -0.0000

Data Index: 865927 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1505. Min Act: -0.0000

Data Index: 277005 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1507. Min Act: -0.0000

Data Index: 460208 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1365. Min Act: -0.0000

Data Index: 762594 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1352. Min Act: -0.0000

Data Index: 362471 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1437. Min Act: -0.0000

Data Index: 523692 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1381. Min Act: -0.0000

Data Index: 943932 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1334. Min Act: -0.0000

Data Index: 819433 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1265. Min Act: -0.0000

Data Index: 935405 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1286. Min Act: -0.0000

Data Index: 234803 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1283. Min Act: -0.0000

Data Index: 795726 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1308. Min Act: -0.0000

Data Index: 652266 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1114882 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1146220 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1286. Min Act: 0.0000

Data Index: 190266 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1286. Min Act: -0.0000

Data Index: 727723 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1319. Min Act: -0.0000

Data Index: 945755 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1275. Min Act: -0.0000

Data Index: 452331 (C4 (Web Text))

Max Activating Token Index: 590