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

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

Neuron 1923 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1097532 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2629. Min Act: -0.0000

Data Index: 501751 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2456. Min Act: -0.0000

Data Index: 874787 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2250. Min Act: -0.0000

Data Index: 752296 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1046774 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1102997 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2066. Min Act: -0.0000

Data Index: 996824 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1962. Min Act: -0.0000

Data Index: 835816 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2046. Min Act: -0.0000

Data Index: 862916 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1998. Min Act: -0.0000

Data Index: 504548 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1313077 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2121. Min Act: -0.0000

Data Index: 271316 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1980. Min Act: -0.0000

Data Index: 466966 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1930. Min Act: -0.0000

Data Index: 419524 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1210027 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1856. Min Act: -0.0000

Data Index: 616387 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1853. Min Act: -0.0000

Data Index: 91845 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1306987 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1870. Min Act: -0.0000

Data Index: 387994 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1755. Min Act: -0.0000

Data Index: 166769 (C4 (Web Text))

Max Activating Token Index: 147