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

Dataset: The Pile

Neuron 1364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.7205. Min Act: -0.0000

Data Index: 505244 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1433832 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5222. Min Act: 0.0000

Data Index: 96035 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1213439 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4609. Min Act: -0.0000

Data Index: 35672 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1380295 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1528214 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1363786 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1288594 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1466288 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4389. Min Act: -0.0000

Data Index: 479719 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1372440 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4204. Min Act: -0.0000

Data Index: 930714 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1391478 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4113. Min Act: -0.0000

Data Index: 957151 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4255. Min Act: -0.0000

Data Index: 127700 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1403422 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1174543 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1931717 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1168227 (The Pile)

Max Activating Token Index: 786