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

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

Neuron 3759 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.6779. Min Act: -0.0000

Data Index: 1572326 (Python Code)

Max Activating Token Index: 872

Text #1

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.5853. Min Act: -0.0000

Data Index: 1535871 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.0269. Min Act: -0.0000

Data Index: 518390 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.3659. Min Act: -0.0000

Data Index: 1573574 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.2312. Min Act: -0.0000

Data Index: 728350 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.2921. Min Act: -0.0000

Data Index: 478467 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.7148. Min Act: -0.0000

Data Index: 1445333 (Python Code)

Max Activating Token Index: 944

Text #7

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.7941. Min Act: -0.0000

Data Index: 970555 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 3.6779. Min Range: -3.6779

Max Act: 3.0850. Min Act: -0.0000

Data Index: 1214480 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1099991 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.7103. Min Act: -0.0000

Data Index: 1352813 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.8361. Min Act: -0.0000

Data Index: 1510817 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.6753. Min Act: -0.0000

Data Index: 1577174 (Python Code)

Max Activating Token Index: 543

Text #13

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.7994. Min Act: -0.0000

Data Index: 370918 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.5149. Min Act: -0.0000

Data Index: 818750 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.6048. Min Act: -0.0000

Data Index: 1540655 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.5580. Min Act: -0.0000

Data Index: 1439081 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.5611. Min Act: -0.0000

Data Index: 1393443 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1390296 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 3.6779. Min Range: -3.6779

Max Act: 2.6632. Min Act: -0.0000

Data Index: 871117 (C4 (Web Text))

Max Activating Token Index: 364