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

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

Neuron 3232 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1205. Min Act: -0.0000

Data Index: 951533 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1096384 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1186. Min Act: -0.0000

Data Index: 357135 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0000

Data Index: 424488 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1303084 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1144. Min Act: -0.0000

Data Index: 382089 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1099. Min Act: -0.0000

Data Index: 744874 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1044. Min Act: -0.0000

Data Index: 76909 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1068. Min Act: -0.0000

Data Index: 75536 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1074. Min Act: -0.0000

Data Index: 449900 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1051. Min Act: -0.0000

Data Index: 756547 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1077. Min Act: -0.0000

Data Index: 404613 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0990. Min Act: -0.0000

Data Index: 964596 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1054. Min Act: -0.0000

Data Index: 592021 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1203672 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1249607 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0936. Min Act: -0.0000

Data Index: 204509 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1256288 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1188621 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0929. Min Act: -0.0000

Data Index: 782700 (C4 (Web Text))

Max Activating Token Index: 128