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

Dataset: The Pile

Neuron 391 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: 0.5934. Min Range: -0.5934

Max Act: 0.5870. Min Act: -0.0000

Data Index: 291102 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5934. Min Act: -0.0000

Data Index: 256565 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1189317 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5909. Min Act: -0.0000

Data Index: 781535 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5303. Min Act: -0.0000

Data Index: 892393 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5154. Min Act: -0.0000

Data Index: 149684 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5566. Min Act: -0.0000

Data Index: 858335 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1553441 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5497. Min Act: -0.0000

Data Index: 965897 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5104. Min Act: -0.0000

Data Index: 755148 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1391276 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5158. Min Act: -0.0000

Data Index: 835150 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1395117 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1283179 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1718689 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1459304 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1674456 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1662252 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1423432 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1386472 (The Pile)

Max Activating Token Index: 163