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

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

Neuron 3475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1150523 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0851. Min Act: -0.0003

Data Index: 91105 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0767. Min Act: -0.0002

Data Index: 13451 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1209091 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0674. Min Act: -0.0002

Data Index: 888051 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1123570 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0725. Min Act: -0.0003

Data Index: 883650 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1051436 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1348272 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0656. Min Act: -0.0002

Data Index: 313681 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0728. Min Act: -0.0003

Data Index: 511858 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0620. Min Act: -0.0002

Data Index: 732410 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0667. Min Act: -0.0002

Data Index: 140090 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0659. Min Act: -0.0002

Data Index: 139039 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1337291 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0644. Min Act: -0.0002

Data Index: 617197 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1056514 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0729. Min Act: -0.0003

Data Index: 408241 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1269239 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1193977 (C4 (Web Text))

Max Activating Token Index: 470