Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 836 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1466852 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1714770 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1787654 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1014080 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7206. Min Act: -0.0000

Data Index: 38829 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.7086. Min Act: -0.0000

Data Index: 735469 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1715824 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6574. Min Act: -0.0000

Data Index: 504213 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6249. Min Act: -0.0000

Data Index: 691922 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1535127 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1326110 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1796818 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1253488 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1403819 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6454. Min Act: -0.0000

Data Index: 219021 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6380. Min Act: -0.0000

Data Index: 933555 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1934497 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6309. Min Act: -0.0000

Data Index: 303322 (The Pile)

Max Activating Token Index: 168

Text #18

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1442585 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 0.8854. Min Range: -0.8854

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1263963 (The Pile)

Max Activating Token Index: 351