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

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

Neuron 3748 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1196319 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1089. Min Act: -0.0002

Data Index: 719677 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1017. Min Act: -0.0002

Data Index: 3604 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1006. Min Act: -0.0002

Data Index: 579555 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1017. Min Act: -0.0002

Data Index: 783992 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1026349 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1004. Min Act: -0.0002

Data Index: 615667 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0963. Min Act: -0.0002

Data Index: 4623 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1593178 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0972. Min Act: -0.0002

Data Index: 925470 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1105249 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0964. Min Act: -0.0002

Data Index: 500314 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1475923 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1197833 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0942. Min Act: -0.0002

Data Index: 914777 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0998. Min Act: -0.0002

Data Index: 767862 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1157189 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0958. Min Act: -0.0002

Data Index: 356079 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0956. Min Act: -0.0002

Data Index: 860398 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1624047 (Python Code)

Max Activating Token Index: 5