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

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

Neuron 808 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.9245. Min Act: -0.0000

Data Index: 85270 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.8637. Min Act: 0.0000

Data Index: 839867 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7629. Min Act: 0.0000

Data Index: 978863 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7602. Min Act: -0.0000

Data Index: 730929 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7181. Min Act: -0.0000

Data Index: 106599 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7644. Min Act: -0.0000

Data Index: 605760 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7169. Min Act: -0.0000

Data Index: 497256 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6762. Min Act: -0.0000

Data Index: 592973 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6967. Min Act: -0.0000

Data Index: 29124 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6501. Min Act: 0.0000

Data Index: 437507 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.7017. Min Act: -0.0000

Data Index: 659933 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6674. Min Act: -0.0000

Data Index: 719624 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6327. Min Act: -0.0000

Data Index: 365435 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6471. Min Act: -0.0000

Data Index: 204731 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6045. Min Act: -0.0000

Data Index: 785907 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.5838. Min Act: -0.0000

Data Index: 991376 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.5987. Min Act: 0.0000

Data Index: 84919 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1331171 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.5771. Min Act: 0.0000

Data Index: 48436 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.9245. Min Range: -0.9245

Max Act: 0.6103. Min Act: -0.0000

Data Index: 122502 (C4 (Web Text))

Max Activating Token Index: 651