Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0001

Data Index: 741760 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0993. Min Act: -0.0001

Data Index: 786000 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0959. Min Act: -0.0001

Data Index: 198885 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0901. Min Act: -0.0001

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0927. Min Act: -0.0001

Data Index: 987272 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1260396 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0870. Min Act: -0.0001

Data Index: 624940 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0886. Min Act: -0.0001

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0800. Min Act: -0.0001

Data Index: 295984 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0775. Min Act: -0.0001

Data Index: 911090 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1055640 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0590. Min Act: -0.0002

Data Index: 75552 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0631. Min Act: -0.0002

Data Index: 620525 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0593. Min Act: -0.0001

Data Index: 214896 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1294092 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1269997 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1036965 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0535. Min Act: -0.0002

Data Index: 38677 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1145823 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0516. Min Act: -0.0001

Data Index: 596360 (C4 (Web Text))

Max Activating Token Index: 723