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

Dataset: The Pile

Neuron 4159 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: 0.7036. Min Range: -0.7036

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1334994 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1865244 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6854. Min Act: -0.0000

Data Index: 401652 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6479. Min Act: -0.0000

Data Index: 515500 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6447. Min Act: -0.0000

Data Index: 725622 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1989830 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6192. Min Act: -0.0000

Data Index: 48431 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1689249 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1984414 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6170. Min Act: -0.0000

Data Index: 719996 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1948172 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1401150 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1253825 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1647155 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1756080 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1009938 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1238713 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5948. Min Act: -0.0000

Data Index: 901611 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6327. Min Act: -0.0000

Data Index: 417332 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1971557 (The Pile)

Max Activating Token Index: 253