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

Dataset: The Pile

Neuron 4209 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1941823 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4163. Min Act: -0.0000

Data Index: 990654 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1597829 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4158. Min Act: -0.0000

Data Index: 39146 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3896. Min Act: -0.0000

Data Index: 169928 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4201. Min Act: -0.0000

Data Index: 894381 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1114228 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4026. Min Act: -0.0000

Data Index: 465097 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1137100 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1682170 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1698768 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1663211 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3672. Min Act: -0.0000

Data Index: 337389 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1047906 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1201190 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3665. Min Act: -0.0000

Data Index: 691866 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3280. Min Act: -0.0000

Data Index: 322120 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3513. Min Act: -0.0000

Data Index: 761666 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3465. Min Act: -0.0000

Data Index: 657315 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 0.5088. Min Range: -0.5088

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1673167 (The Pile)

Max Activating Token Index: 719