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

Dataset: The Pile

Neuron 3680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1583112 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4097. Min Act: -0.0000

Data Index: 221408 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1853465 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1917733 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1901421 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1557209 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1957928 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1500003 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3846. Min Act: -0.0000

Data Index: 870191 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1627359 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4075. Min Act: -0.0000

Data Index: 928196 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3930. Min Act: -0.0000

Data Index: 754203 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3745. Min Act: -0.0000

Data Index: 807244 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3660. Min Act: -0.0000

Data Index: 116415 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3894. Min Act: -0.0000

Data Index: 422339 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1838745 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1715147 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3313. Min Act: -0.0000

Data Index: 961113 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1995058 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3494. Min Act: -0.0000

Data Index: 900558 (The Pile)

Max Activating Token Index: 481