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

Dataset: The Pile

Neuron 28 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: 0.6428. Min Range: -0.6428

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1137778 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5843. Min Act: -0.0000

Data Index: 920996 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1702734 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5697. Min Act: -0.0000

Data Index: 361285 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1820861 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5515. Min Act: -0.0000

Data Index: 257188 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5995. Min Act: -0.0000

Data Index: 630182 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4765. Min Act: -0.0000

Data Index: 466593 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5038. Min Act: -0.0000

Data Index: 870186 (The Pile)

Max Activating Token Index: 555

Text #9

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5115. Min Act: -0.0000

Data Index: 433731 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5206. Min Act: -0.0000

Data Index: 980254 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5082. Min Act: -0.0000

Data Index: 53968 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5181. Min Act: -0.0000

Data Index: 383697 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1194408 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5343. Min Act: -0.0000

Data Index: 277216 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5051. Min Act: -0.0000

Data Index: 41775 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1582491 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1838781 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1320182 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.6428. Min Range: -0.6428

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1539476 (The Pile)

Max Activating Token Index: 330