Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 480 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0005

Data Index: 239803 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0684. Min Act: -0.0005

Data Index: 14169 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0672. Min Act: -0.0005

Data Index: 1250544 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0637. Min Act: -0.0005

Data Index: 589989 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0664. Min Act: -0.0005

Data Index: 208510 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0682. Min Act: -0.0005

Data Index: 337875 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0673. Min Act: -0.0005

Data Index: 800964 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0634. Min Act: -0.0005

Data Index: 757714 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0596. Min Act: -0.0005

Data Index: 93940 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0671. Min Act: -0.0005

Data Index: 8785 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0642. Min Act: -0.0005

Data Index: 212626 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0612. Min Act: -0.0005

Data Index: 428313 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0617. Min Act: -0.0005

Data Index: 215478 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0618. Min Act: -0.0005

Data Index: 951101 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0591. Min Act: -0.0005

Data Index: 469661 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0603. Min Act: -0.0005

Data Index: 13039 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0588. Min Act: -0.0005

Data Index: 613640 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0588. Min Act: -0.0005

Data Index: 431724 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0621. Min Act: -0.0005

Data Index: 985232 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0616. Min Act: -0.0005

Data Index: 165686 (C4 (Web Text))

Max Activating Token Index: 595