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

Dataset: The Pile

Neuron 2658 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 226584 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1266. Min Act: -0.0000

Data Index: 270457 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1638943 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1056. Min Act: -0.0000

Data Index: 533896 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1484261 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1049. Min Act: -0.0000

Data Index: 414793 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1033. Min Act: -0.0000

Data Index: 743432 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1584082 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0909. Min Act: -0.0000

Data Index: 229678 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1001. Min Act: -0.0000

Data Index: 10329 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1170238 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0853. Min Act: -0.0000

Data Index: 414171 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1752989 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1994107 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0900. Min Act: -0.0000

Data Index: 484869 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1757922 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1794790 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1088899 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1220942 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1227305 (The Pile)

Max Activating Token Index: 422