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

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

Neuron 3149 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: 0.9811. Min Range: -0.9811

Max Act: 0.9458. Min Act: -0.0001

Data Index: 176854 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9642. Min Act: -0.0001

Data Index: 1320063 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9073. Min Act: -0.0001

Data Index: 361696 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9811. Min Act: -0.0001

Data Index: 1160227 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9198. Min Act: -0.0001

Data Index: 660456 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8333. Min Act: -0.0001

Data Index: 758317 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8223. Min Act: -0.0001

Data Index: 988223 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8772. Min Act: -0.0001

Data Index: 1206920 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1137489 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8707. Min Act: -0.0001

Data Index: 549353 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8105. Min Act: -0.0001

Data Index: 656530 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8573. Min Act: -0.0001

Data Index: 916196 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8529. Min Act: -0.0000

Data Index: 212580 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9091. Min Act: -0.0000

Data Index: 598433 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9076. Min Act: -0.0001

Data Index: 876269 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9349. Min Act: -0.0001

Data Index: 436504 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.9264. Min Act: -0.0001

Data Index: 586025 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8087. Min Act: -0.0001

Data Index: 989385 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1356542 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.9811. Min Range: -0.9811

Max Act: 0.8574. Min Act: -0.0001

Data Index: 93990 (C4 (Web Text))

Max Activating Token Index: 943