Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2631 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0003

Data Index: 598896 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0868. Min Act: -0.0003

Data Index: 403478 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1321413 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0884. Min Act: -0.0003

Data Index: 692636 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0842. Min Act: -0.0003

Data Index: 1554289 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0859. Min Act: -0.0003

Data Index: 485824 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0824. Min Act: -0.0003

Data Index: 50628 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1850743 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0836. Min Act: -0.0003

Data Index: 1809134 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0786. Min Act: -0.0003

Data Index: 668749 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0811. Min Act: -0.0003

Data Index: 501225 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0809. Min Act: -0.0003

Data Index: 945699 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0801. Min Act: -0.0003

Data Index: 118455 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0795. Min Act: -0.0003

Data Index: 875890 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0757. Min Act: -0.0003

Data Index: 869501 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0789. Min Act: -0.0003

Data Index: 362902 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0817. Min Act: -0.0003

Data Index: 515915 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1126561 (The Pile)

Max Activating Token Index: 238

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0779. Min Act: -0.0003

Data Index: 84805 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1908698 (The Pile)

Max Activating Token Index: 130