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

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

Neuron 2390 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1063580 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0903. Min Act: -0.0000

Data Index: 972646 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0313. Min Act: -0.0000

Data Index: 518498 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1125497 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9884. Min Act: -0.0000

Data Index: 852810 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1353070 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9544. Min Act: -0.0000

Data Index: 833249 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1059838 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1197261 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1340540 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8972. Min Act: 0.0000

Data Index: 1033299 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9013. Min Act: -0.0000

Data Index: 867506 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9033. Min Act: -0.0000

Data Index: 906258 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1105923 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1302459 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8970. Min Act: -0.0000

Data Index: 622863 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1304822 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8445. Min Act: -0.0000

Data Index: 18759 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8151. Min Act: -0.0000

Data Index: 204369 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8854. Min Act: -0.0000

Data Index: 142695 (C4 (Web Text))

Max Activating Token Index: 1008