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

Dataset: The Pile

Neuron 1028 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1669940 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1243579 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5499. Min Act: -0.0000

Data Index: 184959 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5114. Min Act: -0.0000

Data Index: 673859 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1550735 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4619. Min Act: -0.0000

Data Index: 704843 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1976151 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4853. Min Act: -0.0000

Data Index: 981545 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4633. Min Act: -0.0000

Data Index: 570001 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1949872 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1056847 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1257906 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1559547 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1925181 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1389637 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1799804 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1899454 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1289100 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4510. Min Act: -0.0000

Data Index: 799535 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.5499. Min Range: -0.5499

Max Act: 0.4620. Min Act: -0.0000

Data Index: 23696 (The Pile)

Max Activating Token Index: 165