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

Dataset: The Pile

Neuron 3967 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.9279. Min Act: -0.0000

Data Index: 1906638 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1891889 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.8596. Min Act: -0.0000

Data Index: 624717 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1880173 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6373. Min Act: -0.0000

Data Index: 210741 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1660963 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5826. Min Act: -0.0000

Data Index: 811977 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1007624 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.5843. Min Act: -0.0000

Data Index: 611372 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3849. Min Act: -0.0000

Data Index: 280648 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1143160 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1087411 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1057547 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3919. Min Act: -0.0000

Data Index: 990253 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1338713 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1364353 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1282729 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1835814 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1241453 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 1.9279. Min Range: -1.9279

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1184832 (The Pile)

Max Activating Token Index: 889