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

Dataset: The Pile

Neuron 3191 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: 1.3390. Min Range: -1.3390

Max Act: 1.2955. Min Act: -0.0000

Data Index: 265932 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1353361 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2095. Min Act: -0.0000

Data Index: 656306 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1935. Min Act: -0.0000

Data Index: 795827 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1516206 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1440626 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1298045 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2396. Min Act: -0.0000

Data Index: 401667 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1734223 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2101. Min Act: -0.0000

Data Index: 922515 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1199378 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1694188 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1238667 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1841403 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1334489 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2007. Min Act: -0.0000

Data Index: 501795 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1196. Min Act: -0.0000

Data Index: 328745 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1925. Min Act: -0.0000

Data Index: 127295 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1200. Min Act: -0.0000

Data Index: 362147 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1782366 (The Pile)

Max Activating Token Index: 473