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

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

Neuron 105 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: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0002

Data Index: 632933 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1073133 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0710. Min Act: -0.0002

Data Index: 299787 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0738. Min Act: -0.0002

Data Index: 409502 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1311460 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0739. Min Act: -0.0002

Data Index: 391163 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0673. Min Act: -0.0002

Data Index: 378037 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0702. Min Act: -0.0002

Data Index: 640583 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1020836 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0699. Min Act: -0.0002

Data Index: 922890 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0702. Min Act: -0.0002

Data Index: 804860 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0703. Min Act: -0.0002

Data Index: 407238 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1088472 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0656. Min Act: -0.0002

Data Index: 944055 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0625. Min Act: -0.0002

Data Index: 10257 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1131925 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0670. Min Act: -0.0002

Data Index: 516139 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1268855 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0689. Min Act: -0.0002

Data Index: 556110 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0679. Min Act: -0.0002

Data Index: 130250 (C4 (Web Text))

Max Activating Token Index: 483