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

Dataset: The Pile

Neuron 3608 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: 0.6737. Min Range: -0.6737

Max Act: 0.6737. Min Act: 0.0000

Data Index: 20101 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6631. Min Act: -0.0000

Data Index: 568530 (The Pile)

Max Activating Token Index: 64

Text #2

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1915659 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5950. Min Act: -0.0000

Data Index: 813014 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1202242 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1465774 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1281885 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1039173 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5667. Min Act: -0.0000

Data Index: 349001 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1547310 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5542. Min Act: -0.0000

Data Index: 916353 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5627. Min Act: -0.0000

Data Index: 785120 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1157479 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5111. Min Act: -0.0000

Data Index: 803585 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1155250 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5370. Min Act: -0.0000

Data Index: 92015 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5147. Min Act: -0.0000

Data Index: 686572 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.4652. Min Act: -0.0000

Data Index: 206973 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1841156 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5204. Min Act: -0.0000

Data Index: 158494 (The Pile)

Max Activating Token Index: 764