Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3800 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: 0.0000

Data Index: 1793916 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0733. Min Act: -0.0000

Data Index: 630937 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0673. Min Act: -0.0000

Data Index: 820658 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0667. Min Act: -0.0000

Data Index: 621765 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0660. Min Act: -0.0000

Data Index: 301908 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1342122 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0667. Min Act: -0.0000

Data Index: 538511 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1660931 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0654. Min Act: 0.0000

Data Index: 456428 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0646. Min Act: -0.0000

Data Index: 608312 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1315094 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1006780 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1065515 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1785153 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0634. Min Act: 0.0000

Data Index: 1109407 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0605. Min Act: -0.0000

Data Index: 469971 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0595. Min Act: -0.0000

Data Index: 431401 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0589. Min Act: -0.0000

Data Index: 67706 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0587. Min Act: -0.0000

Data Index: 386804 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1275971 (The Pile)

Max Activating Token Index: 554