Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1047 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4653. Min Act: -0.0000

Data Index: 877353 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4114. Min Act: 0.0000

Data Index: 432223 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4219. Min Act: 0.0000

Data Index: 1345878 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4052. Min Act: -0.0000

Data Index: 389533 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4058. Min Act: 0.0000

Data Index: 1746212 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1561792 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1239955 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3805. Min Act: -0.0000

Data Index: 920372 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1818635 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3378. Min Act: -0.0000

Data Index: 496111 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1739668 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3563. Min Act: -0.0000

Data Index: 74116 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1900269 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1933282 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1828259 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1932209 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1446425 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1726173 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3042. Min Act: 0.0000

Data Index: 287825 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3394. Min Act: -0.0000

Data Index: 874437 (The Pile)

Max Activating Token Index: 125