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

Dataset: The Pile

Neuron 1437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1072314 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3301. Min Act: -0.0000

Data Index: 657108 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3299. Min Act: -0.0000

Data Index: 524769 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1133271 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3200. Min Act: -0.0000

Data Index: 90562 (The Pile)

Max Activating Token Index: 992

Text #5

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1041129 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1575941 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3115. Min Act: -0.0000

Data Index: 402437 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3424. Min Act: -0.0000

Data Index: 152994 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2928. Min Act: -0.0000

Data Index: 676294 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1333254 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1594298 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2770. Min Act: -0.0000

Data Index: 513687 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1335391 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1560612 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1116707 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1545889 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1824273 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2694. Min Act: -0.0000

Data Index: 700970 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2560. Min Act: -0.0000

Data Index: 145164 (The Pile)

Max Activating Token Index: 612