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

Dataset: The Pile

Neuron 3537 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: 0.4339. Min Range: -0.4339

Max Act: 0.4178. Min Act: -0.0000

Data Index: 435187 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1350137 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1647340 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1067797 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1615539 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3750. Min Act: -0.0000

Data Index: 315435 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3098. Min Act: -0.0000

Data Index: 884953 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1357729 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3496. Min Act: -0.0000

Data Index: 602801 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1148538 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3459. Min Act: -0.0000

Data Index: 99487 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3558. Min Act: -0.0000

Data Index: 930094 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1163303 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3508. Min Act: -0.0000

Data Index: 706544 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3274. Min Act: -0.0000

Data Index: 365325 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1998505 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1258366 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1847160 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1262369 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3195. Min Act: -0.0000

Data Index: 228095 (The Pile)

Max Activating Token Index: 475