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

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

Neuron 3016 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0002

Data Index: 700201 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1341831 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0911. Min Act: -0.0002

Data Index: 861093 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0882. Min Act: -0.0002

Data Index: 301376 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1156041 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0817. Min Act: -0.0002

Data Index: 332126 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0804. Min Act: -0.0002

Data Index: 680908 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0786. Min Act: -0.0003

Data Index: 211088 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0748. Min Act: -0.0002

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0744. Min Act: -0.0002

Data Index: 255687 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0730. Min Act: -0.0002

Data Index: 790284 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0708. Min Act: -0.0003

Data Index: 505294 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1026073 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0688. Min Act: -0.0002

Data Index: 554431 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1078244 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0686. Min Act: -0.0002

Data Index: 86665 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0671. Min Act: -0.0002

Data Index: 620344 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1126932 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1354466 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0681. Min Act: -0.0002

Data Index: 58764 (C4 (Web Text))

Max Activating Token Index: 19