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

Dataset: The Pile

Neuron 2099 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1158. Min Range: -1.1158

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1330080 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1889742 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8922. Min Act: 0.0000

Data Index: 1501409 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1389533 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1992817 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1260269 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7973. Min Act: -0.0000

Data Index: 424858 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1654280 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7248. Min Act: -0.0000

Data Index: 844667 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6757. Min Act: -0.0000

Data Index: 554372 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6880. Min Act: -0.0000

Data Index: 880696 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6899. Min Act: -0.0000

Data Index: 314537 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1401990 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6819. Min Act: -0.0000

Data Index: 870318 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6608. Min Act: -0.0000

Data Index: 90789 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1351338 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.7261. Min Act: -0.0000

Data Index: 324076 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6484. Min Act: -0.0000

Data Index: 58789 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1044522 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 1.1158. Min Range: -1.1158

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1114669 (The Pile)

Max Activating Token Index: 806