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

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

Neuron 834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0920. Min Range: -6.0920

Max Act: 6.0920. Min Act: -0.0000

Data Index: 395522 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.6269. Min Act: -0.0000

Data Index: 1057916 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.3762. Min Act: -0.0000

Data Index: 656693 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.3630. Min Act: -0.0000

Data Index: 677591 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.3408. Min Act: -0.0000

Data Index: 389127 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.1586. Min Act: -0.0000

Data Index: 20530 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.9892. Min Act: -0.0000

Data Index: 456158 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.0198. Min Act: -0.0000

Data Index: 879604 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.9989. Min Act: -0.0000

Data Index: 73871 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.7856. Min Act: -0.0000

Data Index: 653636 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 6.0920. Min Range: -6.0920

Max Act: 5.0868. Min Act: -0.0000

Data Index: 66081 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.6013. Min Act: -0.0000

Data Index: 652722 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.5462. Min Act: -0.0000

Data Index: 428827 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.5001. Min Act: -0.0000

Data Index: 110643 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.6574. Min Act: -0.0000

Data Index: 675633 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.6606. Min Act: -0.0000

Data Index: 740675 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.4534. Min Act: -0.0000

Data Index: 483035 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.7808. Min Act: -0.0000

Data Index: 216550 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.2872. Min Act: -0.0000

Data Index: 1101031 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 6.0920. Min Range: -6.0920

Max Act: 4.4308. Min Act: -0.0000

Data Index: 173839 (C4 (Web Text))

Max Activating Token Index: 41