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

Dataset: The Pile

Neuron 2819 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.7893. Min Act: -0.0000

Data Index: 224111 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1829004 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.7527. Min Act: -0.0000

Data Index: 215584 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1850647 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1310117 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1338330 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.7247. Min Act: -0.0000

Data Index: 739336 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1422506 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1208553 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6697. Min Act: -0.0000

Data Index: 730498 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6885. Min Act: -0.0000

Data Index: 655639 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6952. Min Act: -0.0000

Data Index: 541715 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6696. Min Act: -0.0000

Data Index: 653219 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6753. Min Act: -0.0000

Data Index: 963596 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1927430 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6108. Min Act: -0.0000

Data Index: 676578 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6615. Min Act: -0.0000

Data Index: 72315 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6725. Min Act: -0.0000

Data Index: 72171 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1315670 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 0.7893. Min Range: -0.7893

Max Act: 0.6495. Min Act: -0.0000

Data Index: 464477 (The Pile)

Max Activating Token Index: 791