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

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

Neuron 1151 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1099038 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2663. Min Act: -0.0000

Data Index: 601438 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2150. Min Act: -0.0000

Data Index: 740175 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2125. Min Act: -0.0001

Data Index: 602455 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1211759 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2032. Min Act: -0.0001

Data Index: 809982 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2008. Min Act: -0.0000

Data Index: 500322 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1124400 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2189. Min Act: -0.0001

Data Index: 114445 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1875. Min Act: -0.0000

Data Index: 981081 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1909. Min Act: -0.0000

Data Index: 182675 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1141814 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1979. Min Act: -0.0001

Data Index: 260825 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1148357 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1750. Min Act: -0.0001

Data Index: 90192 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1824. Min Act: -0.0000

Data Index: 190350 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1113907 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1265624 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1314579 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1883. Min Act: -0.0001

Data Index: 344352 (C4 (Web Text))

Max Activating Token Index: 497