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

Dataset: The Pile

Neuron 1326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1895260 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2654. Min Act: -0.0000

Data Index: 602674 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1826253 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2393. Min Act: -0.0000

Data Index: 788464 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2276. Min Act: -0.0000

Data Index: 269052 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2165. Min Act: -0.0000

Data Index: 566863 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2236. Min Act: -0.0000

Data Index: 529134 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2203. Min Act: -0.0000

Data Index: 182381 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1156866 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1683977 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1982. Min Act: -0.0000

Data Index: 799135 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1971. Min Act: -0.0000

Data Index: 406999 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1123398 (The Pile)

Max Activating Token Index: 725

Text #13

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1735. Min Act: -0.0000

Data Index: 386171 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1381858 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1598772 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2068. Min Act: -0.0000

Data Index: 185121 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1958145 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1919. Min Act: -0.0000

Data Index: 486893 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.1846. Min Act: -0.0000

Data Index: 370279 (The Pile)

Max Activating Token Index: 33