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

Dataset: The Pile

Neuron 1110 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1208. Min Act: -0.0000

Data Index: 31569 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0000

Data Index: 140649 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1116. Min Act: -0.0000

Data Index: 362736 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1119. Min Act: -0.0000

Data Index: 466366 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1464291 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1046. Min Act: -0.0000

Data Index: 857039 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1240339 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1277559 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1352993 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0853. Min Act: -0.0000

Data Index: 981959 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0882. Min Act: -0.0000

Data Index: 354795 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1938297 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0764. Min Act: -0.0000

Data Index: 29973 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1967527 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1009. Min Act: -0.0000

Data Index: 573036 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1343025 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1653552 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0954. Min Act: -0.0000

Data Index: 739993 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1956157 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0899. Min Act: -0.0000

Data Index: 145479 (The Pile)

Max Activating Token Index: 145