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

Dataset: The Pile

Neuron 1422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1984540 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1979178 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6730. Min Act: -0.0000

Data Index: 297877 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6712. Min Act: -0.0000

Data Index: 275394 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5995. Min Act: -0.0000

Data Index: 585700 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6173. Min Act: -0.0000

Data Index: 425930 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1909957 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1820439 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6229. Min Act: -0.0000

Data Index: 514917 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1622654 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1729021 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5715. Min Act: -0.0000

Data Index: 459702 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5498. Min Act: -0.0000

Data Index: 457626 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5639. Min Act: -0.0000

Data Index: 465447 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5485. Min Act: -0.0000

Data Index: 532162 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1371569 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1255703 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1332526 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5440. Min Act: -0.0000

Data Index: 560974 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5286. Min Act: -0.0000

Data Index: 677664 (The Pile)

Max Activating Token Index: 624