Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2208 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0003

Data Index: 1519941 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1444643 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1443297 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1385931 (Python Code)

Max Activating Token Index: 165

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1511509 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1433208 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0747. Min Act: -0.0003

Data Index: 217429 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0776. Min Act: -0.0003

Data Index: 1559329 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1397186 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1421566 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0773. Min Act: -0.0003

Data Index: 1414679 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1568975 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1387068 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0761. Min Act: -0.0003

Data Index: 1461988 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0762. Min Act: -0.0003

Data Index: 1535150 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1365586 (Python Code)

Max Activating Token Index: 395

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1610377 (Python Code)

Max Activating Token Index: 973

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1570137 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1520829 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1597213 (Python Code)

Max Activating Token Index: 840