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

Dataset: The Pile

Neuron 569 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: 0.9373. Min Range: -0.9373

Max Act: 0.9130. Min Act: -0.0000

Data Index: 143077 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1340100 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1762949 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8926. Min Act: -0.0000

Data Index: 26271 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9373. Min Act: -0.0000

Data Index: 145741 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1118989 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9041. Min Act: -0.0000

Data Index: 779000 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9049. Min Act: -0.0000

Data Index: 493996 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8686. Min Act: -0.0000

Data Index: 771801 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1279447 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1117262 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1874595 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1658620 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8265. Min Act: -0.0000

Data Index: 381260 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1842035 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8926. Min Act: -0.0000

Data Index: 359588 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1632350 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8561. Min Act: -0.0000

Data Index: 296418 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8494. Min Act: -0.0000

Data Index: 39892 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1645064 (The Pile)

Max Activating Token Index: 620