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

Dataset: The Pile

Neuron 398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.6890. Min Act: -0.0000

Data Index: 981813 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1380300 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.3974. Min Act: -0.0000

Data Index: 246605 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1241833 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4345. Min Act: -0.0000

Data Index: 595207 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4568. Min Act: -0.0000

Data Index: 894708 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1947493 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4975. Min Act: -0.0000

Data Index: 132700 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4888. Min Act: -0.0000

Data Index: 653835 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.5104. Min Act: -0.0000

Data Index: 187055 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1446407 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.5017. Min Act: -0.0000

Data Index: 689962 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1598163 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4138. Min Act: -0.0000

Data Index: 75598 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.3376. Min Act: -0.0000

Data Index: 597397 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1012376 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4067. Min Act: -0.0000

Data Index: 290105 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1314866 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4785. Min Act: -0.0000

Data Index: 648329 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1608946 (The Pile)

Max Activating Token Index: 720