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

Dataset: The Pile

Neuron 626 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.6418. Min Act: -0.0000

Data Index: 515925 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1153093 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5968. Min Act: -0.0000

Data Index: 371847 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1937590 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1854393 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1911329 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1227142 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1460005 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5646. Min Act: -0.0001

Data Index: 1328321 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5655. Min Act: -0.0000

Data Index: 151068 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5686. Min Act: -0.0000

Data Index: 155512 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5133. Min Act: -0.0000

Data Index: 490194 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1637864 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5253. Min Act: -0.0000

Data Index: 725661 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1531002 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5123. Min Act: -0.0000

Data Index: 451793 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5211. Min Act: -0.0000

Data Index: 55496 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1093546 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1240311 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.6418. Min Range: -0.6418

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1816958 (The Pile)

Max Activating Token Index: 29