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

Dataset: The Pile

Neuron 3310 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.9351. Min Act: -0.0000

Data Index: 244859 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1000313 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1688616 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1933121 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8424. Min Act: -0.0000

Data Index: 819474 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8202. Min Act: -0.0000

Data Index: 745336 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1246674 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1033916 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7263. Min Act: -0.0000

Data Index: 56579 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1373659 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1156302 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7634. Min Act: -0.0000

Data Index: 582649 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7553. Min Act: -0.0000

Data Index: 56366 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1229360 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.6985. Min Act: -0.0000

Data Index: 377079 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7080. Min Act: -0.0000

Data Index: 653895 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1615660 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1053192 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1025449 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1607163 (The Pile)

Max Activating Token Index: 560