Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3032 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1204. Min Act: -0.0001

Data Index: 389714 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1189. Min Act: -0.0001

Data Index: 7868 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1088. Min Act: -0.0000

Data Index: 331325 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1100. Min Act: -0.0001

Data Index: 734963 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1217323 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1075. Min Act: -0.0001

Data Index: 134550 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1032. Min Act: -0.0000

Data Index: 185195 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1036. Min Act: -0.0001

Data Index: 803715 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1060. Min Act: -0.0001

Data Index: 630427 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1019. Min Act: -0.0001

Data Index: 623050 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1011. Min Act: -0.0001

Data Index: 298340 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1035. Min Act: -0.0001

Data Index: 486617 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.1005. Min Act: -0.0001

Data Index: 201617 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0954. Min Act: -0.0001

Data Index: 486756 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0966. Min Act: -0.0001

Data Index: 208761 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1236528 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0893. Min Act: -0.0000

Data Index: 109052 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0948. Min Act: -0.0001

Data Index: 669774 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.1204. Min Range: -0.1204

Max Act: 0.0912. Min Act: -0.0001

Data Index: 454275 (C4 (Web Text))

Max Activating Token Index: 134