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

Dataset: The Pile

Neuron 1844 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1540985 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6253. Min Act: -0.0000

Data Index: 359892 (The Pile)

Max Activating Token Index: 823

Text #2

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1018299 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1211925 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1698115 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5598. Min Act: -0.0000

Data Index: 277588 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5648. Min Act: -0.0000

Data Index: 387624 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5350. Min Act: -0.0000

Data Index: 959735 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5071. Min Act: -0.0000

Data Index: 276349 (The Pile)

Max Activating Token Index: 923

Text #9

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5628. Min Act: -0.0000

Data Index: 632939 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1921785 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1837861 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5045. Min Act: -0.0000

Data Index: 507683 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5013. Min Act: -0.0000

Data Index: 482610 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1426495 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5303. Min Act: -0.0000

Data Index: 147527 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1112654 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5213. Min Act: -0.0000

Data Index: 836014 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5028. Min Act: -0.0000

Data Index: 833899 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1239192 (The Pile)

Max Activating Token Index: 950