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

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

Neuron 4499 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.9278. Min Act: -0.0001

Data Index: 1169606 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.9447. Min Act: -0.0001

Data Index: 1317881 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.8262. Min Act: -0.0001

Data Index: 796300 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.8863. Min Act: -0.0001

Data Index: 492909 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.8982. Min Act: -0.0001

Data Index: 707649 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.7663. Min Act: -0.0001

Data Index: 749334 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.8608. Min Act: -0.0001

Data Index: 695562 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.7229. Min Act: -0.0001

Data Index: 1004516 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.8101. Min Act: -0.0001

Data Index: 100857 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.6794. Min Act: -0.0001

Data Index: 379782 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.7692. Min Act: -0.0001

Data Index: 835906 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.5718. Min Act: -0.0001

Data Index: 424154 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.6371. Min Act: -0.0001

Data Index: 394808 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.6246. Min Act: -0.0001

Data Index: 213204 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.7076. Min Act: -0.0001

Data Index: 455809 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.5944. Min Act: -0.0001

Data Index: 1166303 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.6742. Min Act: -0.0001

Data Index: 709910 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.7913. Min Act: -0.0001

Data Index: 370368 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.4378. Min Act: -0.0001

Data Index: 148184 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.9447. Min Range: -1.9447

Max Act: 1.4960. Min Act: -0.0001

Data Index: 1185726 (C4 (Web Text))

Max Activating Token Index: 551