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

Dataset: The Pile

Neuron 1884 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.7290. Min Act: -0.0000

Data Index: 236943 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1134595 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1176201 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1970991 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4996. Min Act: -0.0000

Data Index: 913977 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4854. Min Act: -0.0000

Data Index: 338564 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4972. Min Act: 0.0000

Data Index: 864353 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1564053 (The Pile)

Max Activating Token Index: 47

Text #8

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4609. Min Act: -0.0000

Data Index: 271233 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1723146 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4856. Min Act: -0.0000

Data Index: 872710 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1842119 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1268378 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4168. Min Act: -0.0000

Data Index: 829911 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1581151 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1266071 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1551505 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4364. Min Act: -0.0000

Data Index: 156498 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4239. Min Act: -0.0000

Data Index: 236403 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.4085. Min Act: 0.0000

Data Index: 1762980 (The Pile)

Max Activating Token Index: 716