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

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

Neuron 2099 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: 0.2264. Min Range: -0.2264

Max Act: 0.2164. Min Act: -0.0003

Data Index: 1184039 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2051. Min Act: -0.0003

Data Index: 877586 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2045. Min Act: -0.0003

Data Index: 476807 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2034. Min Act: -0.0003

Data Index: 554392 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2255. Min Act: -0.0003

Data Index: 145923 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1938. Min Act: -0.0004

Data Index: 630918 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2070. Min Act: -0.0003

Data Index: 1192061 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1990. Min Act: -0.0003

Data Index: 504084 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1925. Min Act: -0.0003

Data Index: 218187 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1975. Min Act: -0.0004

Data Index: 89314 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1829. Min Act: -0.0003

Data Index: 1188251 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1960. Min Act: -0.0003

Data Index: 1162953 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1950. Min Act: -0.0003

Data Index: 1260916 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2264. Min Act: -0.0003

Data Index: 738295 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1885. Min Act: -0.0003

Data Index: 990171 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.2026. Min Act: -0.0004

Data Index: 1212366 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1847. Min Act: -0.0003

Data Index: 888745 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1842. Min Act: -0.0003

Data Index: 167911 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1908. Min Act: -0.0003

Data Index: 663253 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.2264. Min Range: -0.2264

Max Act: 0.1777. Min Act: -0.0004

Data Index: 1214423 (C4 (Web Text))

Max Activating Token Index: 608