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

Dataset: The Pile

Neuron 517 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: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0000

Data Index: 843463 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1105. Min Act: -0.0000

Data Index: 65037 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1053. Min Act: -0.0000

Data Index: 136077 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1854700 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0987. Min Act: -0.0000

Data Index: 392875 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1133809 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1940791 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0982. Min Act: -0.0000

Data Index: 512217 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1697737 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1877432 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0887. Min Act: -0.0000

Data Index: 504615 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1272810 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1981890 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1958262 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1958115 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1390790 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1268482 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1896435 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0802. Min Act: -0.0000

Data Index: 691656 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1685386 (The Pile)

Max Activating Token Index: 797