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

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

Neuron 4839 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2363. Min Range: -8.2363

Max Act: 8.2363. Min Act: -0.0000

Data Index: 167997 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 8.2363. Min Range: -8.2363

Max Act: 7.1787. Min Act: -0.0000

Data Index: 485839 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 8.2363. Min Range: -8.2363

Max Act: 7.0794. Min Act: -0.0000

Data Index: 1348058 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.8131. Min Act: 0.0000

Data Index: 432876 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.9309. Min Act: -0.0000

Data Index: 1206757 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.6927. Min Act: -0.0000

Data Index: 268961 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.2965. Min Act: -0.0000

Data Index: 569911 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.9720. Min Act: -0.0000

Data Index: 573979 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.2707. Min Act: -0.0000

Data Index: 477600 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.9494. Min Act: -0.0000

Data Index: 40016 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.3126. Min Act: -0.0000

Data Index: 41436 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.2847. Min Act: -0.0000

Data Index: 590764 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.9069. Min Act: -0.0000

Data Index: 313655 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.8771. Min Act: -0.0000

Data Index: 61363 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.1815. Min Act: -0.0000

Data Index: 1006683 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.8358. Min Act: -0.0000

Data Index: 134936 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.1522. Min Act: -0.0000

Data Index: 1315695 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 8.2363. Min Range: -8.2363

Max Act: 6.0399. Min Act: -0.0000

Data Index: 959009 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.6947. Min Act: -0.0000

Data Index: 433947 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 8.2363. Min Range: -8.2363

Max Act: 5.8665. Min Act: -0.0000

Data Index: 1065792 (C4 (Web Text))

Max Activating Token Index: 294