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

Dataset: The Pile

Neuron 31 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.2409. Min Act: -0.0000

Data Index: 518520 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.2382. Min Act: -0.0000

Data Index: 523481 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9042. Min Act: -0.0000

Data Index: 346592 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1677779 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1628269 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.0315. Min Act: -0.0000

Data Index: 620390 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 1.2409. Min Range: -1.2409

Max Act: 1.0675. Min Act: -0.0000

Data Index: 578344 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8770. Min Act: 0.0000

Data Index: 1858552 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9752. Min Act: -0.0000

Data Index: 697409 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1508199 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9246. Min Act: -0.0000

Data Index: 233598 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9022. Min Act: -0.0000

Data Index: 119844 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1530224 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1410880 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1366669 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9680. Min Act: -0.0000

Data Index: 840367 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1500529 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1775143 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1326800 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 1.2409. Min Range: -1.2409

Max Act: 0.9136. Min Act: -0.0000

Data Index: 839718 (The Pile)

Max Activating Token Index: 198