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

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

Neuron 1797 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3719. Min Range: -3.3719

Max Act: 3.3422. Min Act: -0.0000

Data Index: 741220 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 3.3719. Min Range: -3.3719

Max Act: 3.3037. Min Act: -0.0000

Data Index: 1003763 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 3.3719. Min Range: -3.3719

Max Act: 3.3719. Min Act: -0.0000

Data Index: 952992 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 3.3719. Min Range: -3.3719

Max Act: 3.2896. Min Act: -0.0000

Data Index: 441966 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 3.3719. Min Range: -3.3719

Max Act: 3.0896. Min Act: -0.0000

Data Index: 741789 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 3.3719. Min Range: -3.3719

Max Act: 3.0133. Min Act: -0.0000

Data Index: 361775 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.8054. Min Act: -0.0000

Data Index: 965231 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.9251. Min Act: -0.0000

Data Index: 1122000 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.9786. Min Act: -0.0000

Data Index: 1193902 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.8629. Min Act: -0.0000

Data Index: 1303869 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.8214. Min Act: -0.0000

Data Index: 226958 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.6654. Min Act: -0.0000

Data Index: 684466 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.8115. Min Act: -0.0000

Data Index: 313754 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.7577. Min Act: -0.0000

Data Index: 881826 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.7706. Min Act: -0.0000

Data Index: 1346718 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.7411. Min Act: -0.0000

Data Index: 816284 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.7274. Min Act: -0.0000

Data Index: 887522 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.7172. Min Act: -0.0000

Data Index: 1123977 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.7058. Min Act: -0.0000

Data Index: 598996 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 3.3719. Min Range: -3.3719

Max Act: 2.6753. Min Act: -0.0000

Data Index: 1248786 (C4 (Web Text))

Max Activating Token Index: 512