Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1280 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2458. Min Act: -0.0002

Data Index: 376137 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2563. Min Act: -0.0002

Data Index: 152237 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2117. Min Act: -0.0002

Data Index: 258841 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2187. Min Act: -0.0002

Data Index: 890534 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2257. Min Act: -0.0002

Data Index: 997140 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2069. Min Act: -0.0002

Data Index: 310088 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2125. Min Act: -0.0002

Data Index: 103409 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2057. Min Act: -0.0002

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2068. Min Act: -0.0002

Data Index: 1129120 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1893. Min Act: -0.0002

Data Index: 651756 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1938. Min Act: -0.0002

Data Index: 622930 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2028. Min Act: -0.0002

Data Index: 509411 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2027. Min Act: -0.0002

Data Index: 1192507 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1895. Min Act: -0.0002

Data Index: 135182 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1901. Min Act: -0.0002

Data Index: 712596 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1928. Min Act: -0.0002

Data Index: 675262 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1931. Min Act: -0.0002

Data Index: 1118680 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1902. Min Act: -0.0002

Data Index: 1173397 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1802. Min Act: -0.0002

Data Index: 602440 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1760. Min Act: -0.0002

Data Index: 113782 (C4 (Web Text))

Max Activating Token Index: 909