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

Dataset: The Pile

Neuron 2521 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: 1.1249. Min Range: -1.1249

Max Act: 1.1249. Min Act: -0.0000

Data Index: 113330 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 1.1249. Min Range: -1.1249

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1075035 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9809. Min Act: -0.0000

Data Index: 813583 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9496. Min Act: -0.0000

Data Index: 874639 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 1.1249. Min Range: -1.1249

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1564941 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9404. Min Act: -0.0000

Data Index: 923156 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1166976 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9302. Min Act: -0.0000

Data Index: 500836 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1375559 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1484971 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9818. Min Act: -0.0000

Data Index: 232567 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9253. Min Act: 0.0000

Data Index: 1307341 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1312700 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9527. Min Act: -0.0000

Data Index: 835630 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1472915 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8840. Min Act: -0.0000

Data Index: 981976 (The Pile)

Max Activating Token Index: 960

Text #16

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9207. Min Act: -0.0000

Data Index: 19362 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1029675 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7892. Min Act: -0.0000

Data Index: 401602 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1885872 (The Pile)

Max Activating Token Index: 391