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

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

Neuron 2502 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: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0002

Data Index: 608035 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0795. Min Act: -0.0002

Data Index: 530172 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0745. Min Act: -0.0002

Data Index: 985167 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0553. Min Act: -0.0002

Data Index: 47808 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0619. Min Act: -0.0002

Data Index: 632796 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0740. Min Act: -0.0002

Data Index: 50716 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0688. Min Act: -0.0002

Data Index: 516762 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0711. Min Act: -0.0002

Data Index: 983186 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0674. Min Act: -0.0002

Data Index: 346495 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0646. Min Act: -0.0002

Data Index: 358760 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0646. Min Act: -0.0002

Data Index: 771732 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1207315 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0733. Min Act: -0.0002

Data Index: 445590 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0653. Min Act: -0.0002

Data Index: 702419 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0720. Min Act: -0.0002

Data Index: 43469 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0642. Min Act: -0.0002

Data Index: 937661 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1224843 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1279110 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0641. Min Act: -0.0002

Data Index: 127373 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0637. Min Act: -0.0002

Data Index: 624350 (C4 (Web Text))

Max Activating Token Index: 922