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

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

Neuron 1899 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1147087 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0760. Min Act: 0.0000

Data Index: 285693 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0722. Min Act: 0.0001

Data Index: 157088 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0697. Min Act: -0.0002

Data Index: 240517 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1185629 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0706. Min Act: -0.0001

Data Index: 831509 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0716. Min Act: 0.0000

Data Index: 445862 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0704. Min Act: 0.0000

Data Index: 1267965 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0682. Min Act: 0.0001

Data Index: 1203842 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0687. Min Act: -0.0001

Data Index: 841797 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0699. Min Act: -0.0001

Data Index: 289200 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0706. Min Act: -0.0002

Data Index: 97227 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0666. Min Act: -0.0002

Data Index: 513915 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0669. Min Act: -0.0002

Data Index: 39172 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0685. Min Act: -0.0001

Data Index: 2132 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0661. Min Act: -0.0001

Data Index: 471595 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0673. Min Act: -0.0002

Data Index: 563913 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0683. Min Act: -0.0002

Data Index: 582469 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0661. Min Act: -0.0001

Data Index: 378651 (C4 (Web Text))

Max Activating Token Index: 717