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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 25 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2177. Min Act: -0.0000

Data Index: 324963 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2163. Min Act: -0.0000

Data Index: 81519 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2010. Min Act: -0.0000

Data Index: 452040 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1134036 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1103859 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2059. Min Act: -0.0000

Data Index: 881820 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1978. Min Act: -0.0000

Data Index: 937763 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2024. Min Act: -0.0000

Data Index: 921208 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1910. Min Act: -0.0000

Data Index: 976431 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1994. Min Act: -0.0000

Data Index: 252212 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1960. Min Act: -0.0000

Data Index: 322035 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1192320 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1925. Min Act: -0.0000

Data Index: 22368 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1048691 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1864. Min Act: -0.0000

Data Index: 914717 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1850. Min Act: -0.0000

Data Index: 94719 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1918. Min Act: -0.0000

Data Index: 504048 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1047751 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1894. Min Act: -0.0000

Data Index: 132489 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.2177. Min Range: -0.2177

Max Act: 0.1895. Min Act: -0.0000

Data Index: 442047 (C4 (Web Text))

Max Activating Token Index: 851