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

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

Neuron 1566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1462630 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0981. Min Act: -0.0002

Data Index: 292518 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1626031 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1563250 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1540320 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1127490 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1505028 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1403399 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1474430 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1204004 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1577995 (Python Code)

Max Activating Token Index: 164

Text #11

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0778. Min Act: -0.0002

Data Index: 484047 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0872. Min Act: -0.0002

Data Index: 333788 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1372022 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0811. Min Act: -0.0002

Data Index: 680393 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0820. Min Act: -0.0002

Data Index: 578047 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0785. Min Act: -0.0002

Data Index: 857659 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1506563 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0802. Min Act: -0.0002

Data Index: 981125 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0824. Min Act: -0.0002

Data Index: 700184 (C4 (Web Text))

Max Activating Token Index: 140