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

Dataset: The Pile

Neuron 1002 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: 1.3463. Min Range: -1.3463

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1215549 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.3463. Min Act: -0.0000

Data Index: 942618 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1833933 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1550212 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.1171. Min Act: -0.0000

Data Index: 599202 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1516314 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1811245 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1046805 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1390440 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.3463. Min Range: -1.3463

Max Act: 1.0052. Min Act: -0.0000

Data Index: 418710 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1174483 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1062080 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9130. Min Act: -0.0000

Data Index: 671167 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1992651 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.8564. Min Act: -0.0000

Data Index: 202590 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1758974 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9809. Min Act: -0.0000

Data Index: 161757 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1154240 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9196. Min Act: -0.0000

Data Index: 718317 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 1.3463. Min Range: -1.3463

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1042669 (The Pile)

Max Activating Token Index: 465