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

Dataset: The Pile

Neuron 1201 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6859. Min Range: -8.6859

Max Act: 8.6859. Min Act: -0.0000

Data Index: 190153 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 8.6859. Min Range: -8.6859

Max Act: 7.7897. Min Act: -0.0000

Data Index: 1689172 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 8.6859. Min Range: -8.6859

Max Act: 8.1431. Min Act: -0.0000

Data Index: 1953948 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 8.6859. Min Range: -8.6859

Max Act: 8.0212. Min Act: -0.0000

Data Index: 1304872 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 8.6859. Min Range: -8.6859

Max Act: 7.4136. Min Act: -0.0000

Data Index: 1873381 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 8.6859. Min Range: -8.6859

Max Act: 7.3823. Min Act: -0.0000

Data Index: 271588 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 8.6859. Min Range: -8.6859

Max Act: 7.1121. Min Act: -0.0000

Data Index: 1129154 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 8.6859. Min Range: -8.6859

Max Act: 7.0737. Min Act: -0.0000

Data Index: 642939 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 8.6859. Min Range: -8.6859

Max Act: 7.2708. Min Act: -0.0000

Data Index: 365299 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.5370. Min Act: -0.0000

Data Index: 417380 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.3150. Min Act: -0.0000

Data Index: 490940 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.8838. Min Act: -0.0000

Data Index: 1335179 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.8698. Min Act: -0.0000

Data Index: 338997 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.4428. Min Act: -0.0000

Data Index: 1366165 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.1698. Min Act: -0.0000

Data Index: 476985 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.2841. Min Act: -0.0000

Data Index: 456731 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.4171. Min Act: -0.0000

Data Index: 1261133 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.4154. Min Act: -0.0000

Data Index: 594817 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.1985. Min Act: -0.0000

Data Index: 507266 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 8.6859. Min Range: -8.6859

Max Act: 6.3568. Min Act: -0.0000

Data Index: 158634 (The Pile)

Max Activating Token Index: 685