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

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

Neuron 3461 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3724. Min Range: -2.3724

Max Act: 2.3724. Min Act: -0.0000

Data Index: 949968 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 2.3724. Min Range: -2.3724

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1260994 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 2.3724. Min Range: -2.3724

Max Act: 2.2761. Min Act: -0.0000

Data Index: 225567 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 2.3724. Min Range: -2.3724

Max Act: 2.2441. Min Act: -0.0000

Data Index: 982677 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 2.3724. Min Range: -2.3724

Max Act: 2.1167. Min Act: -0.0000

Data Index: 1196857 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.9215. Min Act: -0.0000

Data Index: 960105 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.8518. Min Act: -0.0000

Data Index: 519587 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.6534. Min Act: -0.0000

Data Index: 1063708 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.5760. Min Act: -0.0000

Data Index: 96876 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.5532. Min Act: -0.0000

Data Index: 981841 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4165. Min Act: -0.0000

Data Index: 795912 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4247. Min Act: -0.0000

Data Index: 119032 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4348. Min Act: -0.0000

Data Index: 566497 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1187357 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4931. Min Act: -0.0000

Data Index: 324303 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4920. Min Act: -0.0000

Data Index: 333256 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.3984. Min Act: -0.0000

Data Index: 450865 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1038013 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.3901. Min Act: -0.0000

Data Index: 260552 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 2.3724. Min Range: -2.3724

Max Act: 1.4822. Min Act: -0.0000

Data Index: 885080 (C4 (Web Text))

Max Activating Token Index: 539