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

Dataset: The Pile

Neuron 3148 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7890. Min Act: -0.0000

Data Index: 556229 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8877. Min Act: -0.0000

Data Index: 252428 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1683256 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8695. Min Act: -0.0000

Data Index: 115850 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8679. Min Act: -0.0000

Data Index: 23312 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1070879 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1715658 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1355318 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7756. Min Act: -0.0000

Data Index: 622711 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7557. Min Act: -0.0000

Data Index: 631419 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1386677 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1361568 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1084824 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1430914 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1269999 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6294. Min Act: -0.0000

Data Index: 306939 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1125977 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.6868. Min Act: -0.0000

Data Index: 706478 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1538272 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.8877. Min Range: -0.8877

Max Act: 0.7035. Min Act: -0.0000

Data Index: 700118 (The Pile)

Max Activating Token Index: 563