Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0848. Min Act: -0.0000

Data Index: 34751 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1340685 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0801. Min Act: -0.0000

Data Index: 696145 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0746. Min Act: -0.0001

Data Index: 539354 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1062820 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1203803 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0639. Min Act: -0.0000

Data Index: 674203 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0664. Min Act: -0.0000

Data Index: 735466 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0675. Min Act: -0.0000

Data Index: 143195 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0652. Min Act: -0.0001

Data Index: 387241 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0666. Min Act: -0.0000

Data Index: 712930 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1485754 (Python Code)

Max Activating Token Index: 793

Text #12

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0637. Min Act: -0.0001

Data Index: 167533 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0621. Min Act: -0.0001

Data Index: 531724 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0599. Min Act: -0.0001

Data Index: 829624 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1507661 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0628. Min Act: -0.0000

Data Index: 226937 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0552. Min Act: -0.0000

Data Index: 597033 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0550. Min Act: -0.0001

Data Index: 84990 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0566. Min Act: -0.0000

Data Index: 462218 (C4 (Web Text))

Max Activating Token Index: 318