Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1774 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0003

Data Index: 44613 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0708. Min Act: -0.0003

Data Index: 935783 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0727. Min Act: -0.0003

Data Index: 50908 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1220828 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0723. Min Act: -0.0003

Data Index: 803675 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0676. Min Act: -0.0003

Data Index: 293687 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0706. Min Act: -0.0003

Data Index: 638798 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0660. Min Act: -0.0003

Data Index: 525483 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1213585 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0670. Min Act: -0.0003

Data Index: 583557 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1049496 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0670. Min Act: -0.0003

Data Index: 557974 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0662. Min Act: -0.0003

Data Index: 738455 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0680. Min Act: -0.0003

Data Index: 1091562 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0624. Min Act: -0.0003

Data Index: 824417 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1018233 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0645. Min Act: -0.0003

Data Index: 375962 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0629. Min Act: -0.0003

Data Index: 252704 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0655. Min Act: -0.0004

Data Index: 105342 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0672. Min Act: -0.0003

Data Index: 671241 (C4 (Web Text))

Max Activating Token Index: 391