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

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

Neuron 1373 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2179. Min Act: -0.0003

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2178. Min Act: -0.0003

Data Index: 431320 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2092. Min Act: -0.0003

Data Index: 1192568 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2028. Min Act: -0.0003

Data Index: 62717 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2018. Min Act: -0.0003

Data Index: 10298 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.2020. Min Act: -0.0003

Data Index: 491877 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1914. Min Act: -0.0003

Data Index: 1023240 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1961. Min Act: -0.0003

Data Index: 491382 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1999. Min Act: -0.0003

Data Index: 1008221 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1986. Min Act: -0.0003

Data Index: 402099 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1911. Min Act: -0.0003

Data Index: 231645 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1909. Min Act: -0.0003

Data Index: 316652 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1828. Min Act: -0.0003

Data Index: 1078868 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1896. Min Act: -0.0003

Data Index: 789236 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1888. Min Act: -0.0003

Data Index: 1341305 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1889. Min Act: -0.0003

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1829. Min Act: -0.0003

Data Index: 1171833 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1890. Min Act: -0.0003

Data Index: 385004 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1875. Min Act: -0.0003

Data Index: 1340700 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.2179. Min Range: -0.2179

Max Act: 0.1848. Min Act: -0.0003

Data Index: 969099 (C4 (Web Text))

Max Activating Token Index: 1004