Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3065 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.3678. Min Act: -0.0001

Data Index: 749343 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1857. Min Act: -0.0001

Data Index: 1191813 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1428. Min Act: -0.0001

Data Index: 729625 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1241. Min Act: -0.0001

Data Index: 752478 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0551. Min Act: -0.0001

Data Index: 618710 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1211. Min Act: -0.0001

Data Index: 1219722 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0837. Min Act: -0.0001

Data Index: 3197 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0359. Min Act: -0.0001

Data Index: 356270 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0572. Min Act: -0.0001

Data Index: 1074197 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0518. Min Act: -0.0001

Data Index: 474770 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1312669 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0136. Min Act: -0.0001

Data Index: 796892 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9492. Min Act: -0.0001

Data Index: 786181 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0361. Min Act: -0.0001

Data Index: 420898 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.3678. Min Range: -1.3678

Max Act: 1.0027. Min Act: -0.0001

Data Index: 107824 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9700. Min Act: -0.0001

Data Index: 502914 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9702. Min Act: -0.0001

Data Index: 1106974 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9892. Min Act: -0.0001

Data Index: 645519 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.9802. Min Act: -0.0001

Data Index: 331258 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.3678. Min Range: -1.3678

Max Act: 0.8692. Min Act: -0.0001

Data Index: 120653 (C4 (Web Text))

Max Activating Token Index: 752