Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4726 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4417. Min Act: -0.0001

Data Index: 657449 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4509. Min Act: -0.0001

Data Index: 889306 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4371. Min Act: -0.0001

Data Index: 809194 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4194. Min Act: -0.0001

Data Index: 576639 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4244. Min Act: -0.0001

Data Index: 219962 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4170. Min Act: -0.0001

Data Index: 507241 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3807. Min Act: -0.0001

Data Index: 690466 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1179049 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3934. Min Act: -0.0001

Data Index: 1201390 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3540. Min Act: -0.0000

Data Index: 353162 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3630. Min Act: -0.0001

Data Index: 147458 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3623. Min Act: -0.0001

Data Index: 21803 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3680. Min Act: -0.0001

Data Index: 117191 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3539. Min Act: -0.0001

Data Index: 846824 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3434. Min Act: -0.0001

Data Index: 983967 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3185. Min Act: -0.0001

Data Index: 978190 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3523. Min Act: -0.0001

Data Index: 738989 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3338. Min Act: -0.0001

Data Index: 327928 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3650. Min Act: -0.0001

Data Index: 859847 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1109473 (C4 (Web Text))

Max Activating Token Index: 753