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

Dataset: The Pile

Neuron 1051 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1657015 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1217693 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1236516 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.2262. Min Act: -0.0000

Data Index: 1850974 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1972. Min Act: -0.0000

Data Index: 1544133 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1546079 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1196600 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0194. Min Act: -0.0000

Data Index: 579281 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1053353 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 1.5229. Min Range: -1.5229

Max Act: 0.9988. Min Act: -0.0000

Data Index: 705013 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1220. Min Act: -0.0000

Data Index: 151367 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0292. Min Act: -0.0000

Data Index: 146690 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0417. Min Act: -0.0000

Data Index: 704810 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.1048. Min Act: -0.0000

Data Index: 77213 (The Pile)

Max Activating Token Index: 19

Text #14

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0692. Min Act: -0.0000

Data Index: 678001 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1317079 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1729538 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0804. Min Act: -0.0000

Data Index: 753382 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0371. Min Act: -0.0001

Data Index: 1334766 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.5229. Min Range: -1.5229

Max Act: 1.0533. Min Act: -0.0000

Data Index: 336895 (The Pile)

Max Activating Token Index: 734