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

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

Neuron 2807 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0002

Data Index: 84451 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1184159 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1304831 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0060. Min Act: -0.0002

Data Index: 836548 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0060. Min Act: -0.0002

Data Index: 638131 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 144974 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0060. Min Act: -0.0002

Data Index: 655015 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1075994 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1120872 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 199775 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 536921 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 621451 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 845497 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1326471 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 38622 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 261278 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1274192 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 516738 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 913546 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1265771 (C4 (Web Text))

Max Activating Token Index: 561