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

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

Neuron 1125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 962460 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1071. Min Act: -0.0002

Data Index: 295152 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1156652 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0951. Min Act: -0.0002

Data Index: 586639 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0981. Min Act: -0.0002

Data Index: 546147 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0947. Min Act: -0.0002

Data Index: 697442 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0950. Min Act: -0.0002

Data Index: 779995 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0937. Min Act: -0.0002

Data Index: 924661 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1233732 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0940. Min Act: -0.0002

Data Index: 936261 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1086072 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0936. Min Act: -0.0002

Data Index: 660994 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0928. Min Act: -0.0002

Data Index: 746485 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0899. Min Act: -0.0002

Data Index: 947440 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1271700 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0930. Min Act: -0.0002

Data Index: 361668 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0921. Min Act: -0.0002

Data Index: 965092 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0920. Min Act: -0.0002

Data Index: 369676 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0925. Min Act: -0.0002

Data Index: 854403 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0949. Min Act: -0.0002

Data Index: 712560 (C4 (Web Text))

Max Activating Token Index: 34