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

Dataset: The Pile

Neuron 114 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: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0000

Data Index: 883078 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1597866 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1424418 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1136. Min Act: -0.0000

Data Index: 435868 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1023. Min Act: -0.0000

Data Index: 254585 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1847955 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1731313 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0865. Min Act: -0.0000

Data Index: 397715 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1713274 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1135527 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1047822 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0961. Min Act: -0.0000

Data Index: 362104 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1035382 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0906. Min Act: -0.0000

Data Index: 247952 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0918. Min Act: -0.0000

Data Index: 934091 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1836233 (The Pile)

Max Activating Token Index: 958

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1976047 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1736933 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1136837 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1876970 (The Pile)

Max Activating Token Index: 469