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

Dataset: The Pile

Neuron 2372 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: 3.6914. Min Range: -3.6914

Max Act: 3.6485. Min Act: -0.0000

Data Index: 1067717 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6914. Min Act: -0.0000

Data Index: 167540 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6022. Min Act: -0.0000

Data Index: 412931 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.4528. Min Act: -0.0000

Data Index: 560821 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.3181. Min Act: -0.0000

Data Index: 1705509 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.3725. Min Act: -0.0000

Data Index: 1409932 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.2771. Min Act: -0.0000

Data Index: 58233 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1532. Min Act: -0.0000

Data Index: 1457506 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.3016. Min Act: -0.0000

Data Index: 1606213 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.2622. Min Act: -0.0000

Data Index: 1950302 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.0957. Min Act: -0.0000

Data Index: 956571 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.9772. Min Act: -0.0000

Data Index: 496746 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.2213. Min Act: -0.0000

Data Index: 745780 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1702. Min Act: -0.0000

Data Index: 1675082 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.9126. Min Act: -0.0000

Data Index: 1421044 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1746. Min Act: -0.0000

Data Index: 1183775 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1375. Min Act: -0.0000

Data Index: 1397973 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 3.6914. Min Range: -3.6914

Max Act: 2.8976. Min Act: -0.0000

Data Index: 1446588 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1661. Min Act: -0.0000

Data Index: 1375402 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.1228. Min Act: -0.0000

Data Index: 797353 (The Pile)

Max Activating Token Index: 949