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

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

Neuron 3828 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1563042 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1419300 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1468297 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1068. Min Act: -0.0000

Data Index: 518396 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1585699 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1556072 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0928. Min Act: -0.0000

Data Index: 394882 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1558354 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1025981 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1432195 (Python Code)

Max Activating Token Index: 747

Text #11

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0941. Min Act: -0.0000

Data Index: 268153 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0928. Min Act: 0.0001

Data Index: 1137869 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1556872 (Python Code)

Max Activating Token Index: 142

Text #14

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0893. Min Act: -0.0000

Data Index: 654216 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1636308 (Python Code)

Max Activating Token Index: 511

Text #16

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1196855 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1521656 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0823. Min Act: -0.0000

Data Index: 901803 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0846. Min Act: 0.0001

Data Index: 922966 (C4 (Web Text))

Max Activating Token Index: 744