Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5090 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2678. Min Act: -0.0000

Data Index: 115142 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2689. Min Act: -0.0000

Data Index: 839221 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2244. Min Act: -0.0000

Data Index: 154779 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2257. Min Act: 0.0000

Data Index: 116131 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2251. Min Act: -0.0000

Data Index: 620798 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2194. Min Act: 0.0000

Data Index: 409481 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2243. Min Act: -0.0000

Data Index: 422543 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2094. Min Act: -0.0000

Data Index: 98762 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2033. Min Act: -0.0000

Data Index: 76951 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2102. Min Act: -0.0000

Data Index: 104480 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1256774 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1038246 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1118769 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1257540 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1892. Min Act: -0.0000

Data Index: 108347 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1833. Min Act: -0.0000

Data Index: 991173 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1003759 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1818. Min Act: -0.0000

Data Index: 400066 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1864. Min Act: -0.0000

Data Index: 409082 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.2689. Min Range: -0.2689

Max Act: 0.1802. Min Act: -0.0000

Data Index: 789304 (C4 (Web Text))

Max Activating Token Index: 297