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

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

Neuron 2394 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1664. Min Act: -0.0002

Data Index: 26703 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1122. Min Act: -0.0002

Data Index: 974906 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1200. Min Act: -0.0002

Data Index: 119270 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1184. Min Act: -0.0002

Data Index: 723037 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1067. Min Act: -0.0002

Data Index: 155491 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1269. Min Act: -0.0002

Data Index: 295896 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1153. Min Act: -0.0002

Data Index: 458108 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1053. Min Act: -0.0002

Data Index: 220139 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0993. Min Act: -0.0002

Data Index: 218559 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1049. Min Act: -0.0002

Data Index: 130263 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1204541 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1109. Min Act: -0.0002

Data Index: 970494 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1251902 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1047. Min Act: -0.0002

Data Index: 589313 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1242587 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1005. Min Act: -0.0002

Data Index: 866185 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1009. Min Act: -0.0002

Data Index: 982886 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0859. Min Act: -0.0002

Data Index: 765038 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1156723 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0815. Min Act: -0.0002

Data Index: 870867 (C4 (Web Text))

Max Activating Token Index: 239