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

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

Neuron 3570 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0001

Data Index: 46700 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1040. Min Act: -0.0001

Data Index: 878985 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1027. Min Act: -0.0001

Data Index: 637000 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1280715 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0973. Min Act: -0.0001

Data Index: 375714 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0955. Min Act: -0.0001

Data Index: 592230 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0978. Min Act: -0.0001

Data Index: 525393 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1112514 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0909. Min Act: -0.0001

Data Index: 442197 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0875. Min Act: -0.0001

Data Index: 218032 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1015407 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0890. Min Act: -0.0001

Data Index: 823991 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0915. Min Act: -0.0001

Data Index: 726452 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0848. Min Act: -0.0001

Data Index: 909177 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0834. Min Act: -0.0001

Data Index: 477164 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0843. Min Act: -0.0001

Data Index: 874586 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1333268 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0873. Min Act: -0.0001

Data Index: 989310 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0906. Min Act: -0.0001

Data Index: 980500 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0856. Min Act: -0.0001

Data Index: 240303 (C4 (Web Text))

Max Activating Token Index: 109