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

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

Neuron 3603 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: 0.1158. Min Range: -0.1158

Max Act: 0.1158. Min Act: -0.0002

Data Index: 109553 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1155. Min Act: -0.0002

Data Index: 877636 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1144. Min Act: -0.0002

Data Index: 669635 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1103. Min Act: -0.0002

Data Index: 559347 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1086. Min Act: -0.0002

Data Index: 291070 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1187975 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0996. Min Act: -0.0002

Data Index: 450725 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0980. Min Act: -0.0002

Data Index: 640487 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0957. Min Act: -0.0002

Data Index: 461704 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0970. Min Act: -0.0002

Data Index: 884717 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0934. Min Act: -0.0002

Data Index: 996459 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0969. Min Act: -0.0002

Data Index: 528885 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1067071 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0945. Min Act: -0.0002

Data Index: 234864 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1147045 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0886. Min Act: -0.0002

Data Index: 881031 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1175577 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0861. Min Act: -0.0002

Data Index: 775048 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0868. Min Act: -0.0002

Data Index: 918252 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0856. Min Act: -0.0002

Data Index: 529083 (C4 (Web Text))

Max Activating Token Index: 317