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

Dataset: The Pile

Neuron 1898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4596. Min Act: -0.0000

Data Index: 632024 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4256. Min Act: -0.0000

Data Index: 536678 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1732022 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3822. Min Act: -0.0000

Data Index: 194687 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1321069 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3313. Min Act: -0.0000

Data Index: 363265 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3156. Min Act: -0.0000

Data Index: 806084 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1507463 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1731998 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3397. Min Act: -0.0000

Data Index: 605765 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3237. Min Act: -0.0000

Data Index: 667491 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1466496 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3220. Min Act: -0.0000

Data Index: 659063 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1994049 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3426. Min Act: -0.0000

Data Index: 631201 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3178. Min Act: -0.0000

Data Index: 507234 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2925. Min Act: -0.0000

Data Index: 924198 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1235111 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1732046 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3148. Min Act: -0.0000

Data Index: 462200 (The Pile)

Max Activating Token Index: 91