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

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

Neuron 5255 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4035. Min Range: -3.4035

Max Act: 3.4035. Min Act: -0.0000

Data Index: 631573 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.4035. Min Range: -3.4035

Max Act: 3.1031. Min Act: -0.0000

Data Index: 911202 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.7293. Min Act: -0.0000

Data Index: 425067 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.6684. Min Act: -0.0000

Data Index: 521893 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.8417. Min Act: -0.0000

Data Index: 704143 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.7145. Min Act: -0.0000

Data Index: 569191 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.5000. Min Act: -0.0000

Data Index: 576237 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.4639. Min Act: -0.0000

Data Index: 826526 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.5709. Min Act: -0.0000

Data Index: 661161 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.4845. Min Act: -0.0000

Data Index: 270729 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.4643. Min Act: -0.0000

Data Index: 1232699 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.3409. Min Act: -0.0000

Data Index: 884567 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.5988. Min Act: -0.0000

Data Index: 333316 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.5591. Min Act: -0.0000

Data Index: 973862 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.4152. Min Act: -0.0000

Data Index: 833551 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.3895. Min Act: -0.0000

Data Index: 629159 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.3751. Min Act: -0.0000

Data Index: 1187797 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.3680. Min Act: -0.0000

Data Index: 456970 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.1162. Min Act: -0.0000

Data Index: 855647 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 3.4035. Min Range: -3.4035

Max Act: 2.2291. Min Act: -0.0000

Data Index: 591725 (C4 (Web Text))

Max Activating Token Index: 830