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

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

Neuron 1738 in Layer 7

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: 621172 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0811. Min Act: -0.0000

Data Index: 255186 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0728. Min Act: -0.0000

Data Index: 439337 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1072647 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0661. Min Act: -0.0000

Data Index: 50805 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0757. Min Act: -0.0000

Data Index: 175419 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0673. Min Act: -0.0000

Data Index: 33794 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0666. Min Act: -0.0000

Data Index: 11331 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1041708 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1222922 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1400119 (Python Code)

Max Activating Token Index: 557

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0640. Min Act: -0.0000

Data Index: 143731 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0633. Min Act: -0.0000

Data Index: 607967 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0607. Min Act: -0.0000

Data Index: 435669 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0604. Min Act: -0.0000

Data Index: 505710 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0566. Min Act: -0.0000

Data Index: 628177 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0589. Min Act: -0.0000

Data Index: 37981 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0559. Min Act: -0.0000

Data Index: 255474 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1323613 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0590. Min Act: -0.0000

Data Index: 413234 (C4 (Web Text))

Max Activating Token Index: 754