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

Dataset: The Pile

Neuron 2233 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: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1176638 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7913. Min Act: -0.0000

Data Index: 351908 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1713402 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5328. Min Act: -0.0000

Data Index: 54576 (The Pile)

Max Activating Token Index: 97

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6016. Min Act: -0.0000

Data Index: 291943 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1809382 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5832. Min Act: -0.0000

Data Index: 735541 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1006105 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1958713 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5093. Min Act: -0.0000

Data Index: 468410 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4965. Min Act: -0.0000

Data Index: 37402 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1955820 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1262497 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1209685 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1768087 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1508669 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1645136 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4855. Min Act: -0.0000

Data Index: 99624 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5391. Min Act: -0.0000

Data Index: 7018 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1087308 (The Pile)

Max Activating Token Index: 787