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

Dataset: The Pile

Neuron 4710 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: 7.2176. Min Range: -7.2176

Max Act: 7.2176. Min Act: -0.0000

Data Index: 304175 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 7.2176. Min Range: -7.2176

Max Act: 6.4716. Min Act: -0.0000

Data Index: 680539 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 7.2176. Min Range: -7.2176

Max Act: 6.1839. Min Act: -0.0000

Data Index: 1029940 (The Pile)

Max Activating Token Index: 865

Text #3

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.9137. Min Act: -0.0000

Data Index: 1688220 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.7931. Min Act: -0.0000

Data Index: 1603957 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.3192. Min Act: -0.0000

Data Index: 1979912 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.5122. Min Act: -0.0000

Data Index: 1425468 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.3966. Min Act: -0.0000

Data Index: 1480815 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.2431. Min Act: -0.0000

Data Index: 1390844 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.1204. Min Act: -0.0000

Data Index: 914746 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.0164. Min Act: -0.0000

Data Index: 1158974 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.0307. Min Act: -0.0000

Data Index: 1831134 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.5805. Min Act: -0.0000

Data Index: 1070501 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.9007. Min Act: -0.0000

Data Index: 1422294 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.9869. Min Act: -0.0000

Data Index: 1992406 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.4049. Min Act: -0.0000

Data Index: 1438652 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 7.2176. Min Range: -7.2176

Max Act: 5.4378. Min Act: -0.0000

Data Index: 337501 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.4298. Min Act: -0.0000

Data Index: 1597245 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.5553. Min Act: -0.0000

Data Index: 494260 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 7.2176. Min Range: -7.2176

Max Act: 4.3093. Min Act: -0.0000

Data Index: 811481 (The Pile)

Max Activating Token Index: 548