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

Dataset: The Pile

Neuron 3858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1061990 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2256. Min Act: -0.0000

Data Index: 172284 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2057. Min Act: -0.0000

Data Index: 36873 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.3197. Min Act: -0.0000

Data Index: 143483 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1045134 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1958566 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1850. Min Act: -0.0000

Data Index: 195657 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1491743 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1090106 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1558068 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1161. Min Act: -0.0000

Data Index: 337460 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1057330 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1379. Min Act: -0.0000

Data Index: 268922 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0986. Min Act: -0.0000

Data Index: 950931 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1250. Min Act: -0.0000

Data Index: 765532 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1276. Min Act: -0.0000

Data Index: 872275 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1316048 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1055511 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1238334 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1848273 (The Pile)

Max Activating Token Index: 687