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

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

Neuron 945 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.2744. Min Range: -12.2744

Max Act: 12.2744. Min Act: -0.0000

Data Index: 1031606 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 12.2744. Min Range: -12.2744

Max Act: 11.4758. Min Act: -0.0000

Data Index: 512660 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.9504. Min Act: -0.0000

Data Index: 389714 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.7719. Min Act: -0.0000

Data Index: 56757 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.5245. Min Act: -0.0000

Data Index: 30180 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.5134. Min Act: -0.0000

Data Index: 959009 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.3526. Min Act: -0.0000

Data Index: 1348058 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.4136. Min Act: -0.0000

Data Index: 139977 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.3492. Min Act: -0.0000

Data Index: 211807 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 12.2744. Min Range: -12.2744

Max Act: 9.9902. Min Act: -0.0000

Data Index: 594191 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.0193. Min Act: -0.0000

Data Index: 61363 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.1413. Min Act: -0.0000

Data Index: 220881 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.2406. Min Act: -0.0000

Data Index: 351004 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 12.2744. Min Range: -12.2744

Max Act: 9.9354. Min Act: -0.0000

Data Index: 41436 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.2526. Min Act: -0.0000

Data Index: 357200 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.0863. Min Act: -0.0000

Data Index: 187766 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 12.2744. Min Range: -12.2744

Max Act: 10.0626. Min Act: -0.0000

Data Index: 937963 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 12.2744. Min Range: -12.2744

Max Act: 9.9665. Min Act: -0.0000

Data Index: 243089 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 12.2744. Min Range: -12.2744

Max Act: 9.9642. Min Act: -0.0000

Data Index: 523960 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 12.2744. Min Range: -12.2744

Max Act: 9.7819. Min Act: -0.0000

Data Index: 638590 (C4 (Web Text))

Max Activating Token Index: 23