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

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

Neuron 1685 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: 1.1473. Min Range: -1.1473

Max Act: 1.1473. Min Act: -0.0001

Data Index: 22902 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.1473. Min Range: -1.1473

Max Act: 1.0510. Min Act: -0.0001

Data Index: 10388 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9877. Min Act: -0.0001

Data Index: 1019176 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.1473. Min Range: -1.1473

Max Act: 1.0121. Min Act: -0.0001

Data Index: 278000 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9995. Min Act: -0.0001

Data Index: 634685 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9975. Min Act: -0.0001

Data Index: 28393 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1309933 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9641. Min Act: -0.0000

Data Index: 908690 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.1473. Min Range: -1.1473

Max Act: 1.0631. Min Act: -0.0001

Data Index: 558010 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.8057. Min Act: -0.0001

Data Index: 988754 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9047. Min Act: -0.0001

Data Index: 651013 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9343. Min Act: -0.0001

Data Index: 1032076 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9665. Min Act: -0.0001

Data Index: 587308 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.8743. Min Act: -0.0001

Data Index: 631208 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9245. Min Act: -0.0001

Data Index: 1137079 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9244. Min Act: -0.0000

Data Index: 578251 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1070793 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9041. Min Act: -0.0001

Data Index: 1193226 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.8029. Min Act: -0.0001

Data Index: 1137825 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 1.1473. Min Range: -1.1473

Max Act: 0.9262. Min Act: -0.0001

Data Index: 1016961 (C4 (Web Text))

Max Activating Token Index: 404