Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1387 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1037904 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0002

Data Index: 905619 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1139. Min Act: -0.0001

Data Index: 346232 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1170. Min Act: -0.0002

Data Index: 180058 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1348365 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1070. Min Act: -0.0001

Data Index: 591556 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0937. Min Act: -0.0001

Data Index: 928622 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1033502 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1214177 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1174928 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1207018 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1021. Min Act: -0.0002

Data Index: 401648 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1047590 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1305764 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0966. Min Act: -0.0002

Data Index: 693337 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1066844 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1217793 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0931. Min Act: -0.0002

Data Index: 534495 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1214855 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1063. Min Act: -0.0002

Data Index: 936524 (C4 (Web Text))

Max Activating Token Index: 817