Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2903 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1175615 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1318. Min Act: -0.0001

Data Index: 465845 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1318905 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1213. Min Act: -0.0001

Data Index: 899083 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1112. Min Act: -0.0001

Data Index: 225016 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1123. Min Act: -0.0001

Data Index: 185904 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1116. Min Act: -0.0001

Data Index: 705258 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1105. Min Act: -0.0001

Data Index: 446969 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1178484 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1057. Min Act: -0.0001

Data Index: 968690 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1172898 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1063. Min Act: -0.0001

Data Index: 915096 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1025. Min Act: -0.0001

Data Index: 891308 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1039198 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1044. Min Act: -0.0001

Data Index: 751265 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0995. Min Act: -0.0001

Data Index: 193611 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1024. Min Act: -0.0001

Data Index: 337992 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1055. Min Act: -0.0001

Data Index: 353491 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1320141 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1042. Min Act: -0.0001

Data Index: 104211 (C4 (Web Text))

Max Activating Token Index: 632