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

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

Neuron 5290 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1222. Min Range: -5.1222

Max Act: 5.0834. Min Act: -0.0000

Data Index: 856717 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 5.1222. Min Range: -5.1222

Max Act: 5.1222. Min Act: -0.0000

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9494. Min Act: -0.0000

Data Index: 963494 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.5500. Min Act: -0.0000

Data Index: 171832 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7224. Min Act: -0.0000

Data Index: 599486 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9159. Min Act: -0.0000

Data Index: 591126 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1281846 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7058. Min Act: -0.0000

Data Index: 373405 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.4480. Min Act: -0.0000

Data Index: 1250841 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7872. Min Act: -0.0000

Data Index: 837003 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.2039. Min Act: -0.0000

Data Index: 1228016 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7591. Min Act: -0.0000

Data Index: 72260 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7383. Min Act: -0.0000

Data Index: 760332 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.5543. Min Act: -0.0000

Data Index: 1031656 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7560. Min Act: -0.0000

Data Index: 379562 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.7386. Min Act: -0.0000

Data Index: 1038652 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.3689. Min Act: -0.0000

Data Index: 435745 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.5191. Min Act: -0.0000

Data Index: 781982 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.5458. Min Act: -0.0000

Data Index: 457425 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.5423. Min Act: -0.0000

Data Index: 420233 (C4 (Web Text))

Max Activating Token Index: 774