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

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

Neuron 2769 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: 8.3063. Min Range: -8.3063

Max Act: 8.3063. Min Act: -0.0000

Data Index: 578810 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 8.3063. Min Range: -8.3063

Max Act: 6.9539. Min Act: -0.0000

Data Index: 252404 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 8.3063. Min Range: -8.3063

Max Act: 6.7095. Min Act: -0.0000

Data Index: 844949 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 8.3063. Min Range: -8.3063

Max Act: 6.1738. Min Act: -0.0000

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 8.3063. Min Range: -8.3063

Max Act: 5.8642. Min Act: -0.0000

Data Index: 293161 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 8.3063. Min Range: -8.3063

Max Act: 5.4057. Min Act: -0.0000

Data Index: 56542 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 8.3063. Min Range: -8.3063

Max Act: 5.1770. Min Act: -0.0000

Data Index: 1114916 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 8.3063. Min Range: -8.3063

Max Act: 5.3065. Min Act: -0.0000

Data Index: 825723 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 8.3063. Min Range: -8.3063

Max Act: 5.2180. Min Act: -0.0000

Data Index: 50131 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.7136. Min Act: -0.0000

Data Index: 136434 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.8774. Min Act: -0.0000

Data Index: 893974 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.7047. Min Act: -0.0000

Data Index: 638906 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.8426. Min Act: -0.0000

Data Index: 687024 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.6411. Min Act: -0.0000

Data Index: 319421 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.2508. Min Act: -0.0000

Data Index: 451594 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.6213. Min Act: -0.0000

Data Index: 1145799 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.8946. Min Act: -0.0000

Data Index: 596618 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.6516. Min Act: -0.0000

Data Index: 276877 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.1996. Min Act: -0.0000

Data Index: 1107670 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 8.3063. Min Range: -8.3063

Max Act: 4.1103. Min Act: -0.0000

Data Index: 124373 (C4 (Web Text))

Max Activating Token Index: 678