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

Dataset: The Pile

Neuron 1815 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: 0.3386. Min Range: -0.3386

Max Act: 0.3386. Min Act: -0.0000

Data Index: 735372 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3097. Min Act: -0.0000

Data Index: 238249 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1443131 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1658867 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1541269 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2803. Min Act: -0.0000

Data Index: 979368 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1151937 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1890798 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1931780 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2404. Min Act: -0.0000

Data Index: 588616 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2345. Min Act: -0.0000

Data Index: 452325 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1566823 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2274. Min Act: -0.0000

Data Index: 723144 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2273. Min Act: -0.0000

Data Index: 305593 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2361. Min Act: -0.0000

Data Index: 834196 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2204. Min Act: -0.0000

Data Index: 582662 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2101. Min Act: -0.0000

Data Index: 170621 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1996424 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2207. Min Act: -0.0000

Data Index: 449348 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.3386. Min Range: -0.3386

Max Act: 0.2117. Min Act: -0.0000

Data Index: 634722 (The Pile)

Max Activating Token Index: 181