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

Dataset: The Pile

Neuron 1845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4190. Min Act: -0.0000

Data Index: 873191 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1546172 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1936420 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4080. Min Act: -0.0000

Data Index: 55063 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1862264 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1789794 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.4263. Min Act: -0.0000

Data Index: 901924 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3715. Min Act: -0.0000

Data Index: 750138 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1907491 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3464. Min Act: -0.0000

Data Index: 11459 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3444. Min Act: -0.0000

Data Index: 502340 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1124198 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3527. Min Act: -0.0000

Data Index: 647809 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3348. Min Act: -0.0000

Data Index: 231060 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3219. Min Act: -0.0000

Data Index: 183719 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3246. Min Act: -0.0000

Data Index: 29467 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1185543 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1672493 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.2954. Min Act: -0.0000

Data Index: 628210 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.4712. Min Range: -0.4712

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1264802 (The Pile)

Max Activating Token Index: 353