Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5942 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1414179 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0912. Min Act: -0.0000

Data Index: 607904 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1503223 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0770. Min Act: -0.0000

Data Index: 198460 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1435418 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1518166 (Python Code)

Max Activating Token Index: 379

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1605635 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1454667 (Python Code)

Max Activating Token Index: 348

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1609800 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1601589 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1372624 (Python Code)

Max Activating Token Index: 736

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1419454 (Python Code)

Max Activating Token Index: 194

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0654. Min Act: -0.0000

Data Index: 60690 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0691. Min Act: -0.0000

Data Index: 144141 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0626. Min Act: -0.0000

Data Index: 616899 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1578471 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1403980 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1634230 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1096956 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1440528 (Python Code)

Max Activating Token Index: 488