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

Dataset: The Pile

Neuron 2979 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: 3.8850. Min Range: -3.8850

Max Act: 3.8850. Min Act: -0.0000

Data Index: 771257 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.8381. Min Act: -0.0000

Data Index: 1972409 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.3047. Min Act: -0.0000

Data Index: 1935220 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.5401. Min Act: -0.0000

Data Index: 1560940 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.3611. Min Act: -0.0000

Data Index: 699767 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.4391. Min Act: -0.0000

Data Index: 745526 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.3957. Min Act: -0.0000

Data Index: 702908 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.5204. Min Act: -0.0000

Data Index: 391889 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.1693. Min Act: -0.0000

Data Index: 1288154 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.2749. Min Act: -0.0000

Data Index: 983650 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.2724. Min Act: -0.0000

Data Index: 1230943 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 3.8850. Min Range: -3.8850

Max Act: 2.9680. Min Act: -0.0000

Data Index: 531863 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 3.8850. Min Range: -3.8850

Max Act: 2.9494. Min Act: -0.0000

Data Index: 1299667 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.0698. Min Act: -0.0000

Data Index: 1835828 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.0501. Min Act: -0.0000

Data Index: 1547628 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.2043. Min Act: -0.0000

Data Index: 215340 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.0318. Min Act: -0.0000

Data Index: 683726 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.1883. Min Act: -0.0000

Data Index: 1054342 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.0283. Min Act: -0.0000

Data Index: 1489486 (The Pile)

Max Activating Token Index: 45

Text #19

Max Range: 3.8850. Min Range: -3.8850

Max Act: 3.0274. Min Act: -0.0000

Data Index: 98213 (The Pile)

Max Activating Token Index: 554