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

Dataset: The Pile

Neuron 249 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: 0.5132. Min Range: -0.5132

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1273165 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4273. Min Act: -0.0000

Data Index: 310655 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4237. Min Act: -0.0000

Data Index: 213597 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1423179 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.4224. Min Act: -0.0000

Data Index: 227553 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1188079 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3633. Min Act: -0.0000

Data Index: 291783 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3603. Min Act: -0.0000

Data Index: 356451 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3513. Min Act: -0.0000

Data Index: 787658 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1473440 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3514. Min Act: -0.0000

Data Index: 422924 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1351431 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3615. Min Act: -0.0000

Data Index: 340016 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1320652 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3165. Min Act: -0.0000

Data Index: 519761 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3295. Min Act: -0.0000

Data Index: 331335 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3163. Min Act: -0.0000

Data Index: 359145 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3266. Min Act: -0.0000

Data Index: 301001 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1409213 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 0.5132. Min Range: -0.5132

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1083853 (The Pile)

Max Activating Token Index: 786