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

Dataset: The Pile

Neuron 4844 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: 1.1326. Min Range: -1.1326

Max Act: 1.1285. Min Act: 0.0000

Data Index: 1503623 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.1326. Min Range: -1.1326

Max Act: 1.1326. Min Act: -0.0000

Data Index: 766949 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 1.1326. Min Range: -1.1326

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1100164 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8760. Min Act: 0.0000

Data Index: 967209 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1624727 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9320. Min Act: -0.0000

Data Index: 659544 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8999. Min Act: 0.0000

Data Index: 307793 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1825992 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1457392 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9597. Min Act: -0.0000

Data Index: 593559 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8893. Min Act: 0.0001

Data Index: 286226 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1649203 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8878. Min Act: -0.0000

Data Index: 798359 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1031927 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1411616 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8401. Min Act: -0.0000

Data Index: 496405 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8275. Min Act: 0.0000

Data Index: 612083 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1042229 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8165. Min Act: 0.0000

Data Index: 1913880 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1127198 (The Pile)

Max Activating Token Index: 106