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

Dataset: The Pile

Neuron 3397 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.9359. Min Act: -0.0000

Data Index: 434909 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7409. Min Act: -0.0000

Data Index: 862597 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.6887. Min Act: -0.0000

Data Index: 745698 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.7158. Min Act: -0.0000

Data Index: 166728 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5770. Min Act: 0.0000

Data Index: 975729 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1650601 (The Pile)

Max Activating Token Index: 105

Text #6

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5263. Min Act: 0.0000

Data Index: 1887950 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1907915 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5587. Min Act: 0.0000

Data Index: 244190 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1938987 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5064. Min Act: 0.0000

Data Index: 270057 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5887. Min Act: 0.0000

Data Index: 1693101 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5260. Min Act: 0.0000

Data Index: 1399841 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5159. Min Act: -0.0000

Data Index: 839354 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1062433 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5208. Min Act: 0.0000

Data Index: 1510907 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.4889. Min Act: 0.0000

Data Index: 792194 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5169. Min Act: 0.0000

Data Index: 1612279 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.5056. Min Act: -0.0000

Data Index: 654596 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 0.9359. Min Range: -0.9359

Max Act: 0.4748. Min Act: 0.0000

Data Index: 1681826 (The Pile)

Max Activating Token Index: 470