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

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

Neuron 166 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0003

Data Index: 496687 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0846. Min Act: -0.0003

Data Index: 452519 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0804. Min Act: -0.0003

Data Index: 465825 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0793. Min Act: -0.0003

Data Index: 182014 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0754. Min Act: -0.0002

Data Index: 370782 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0740. Min Act: -0.0003

Data Index: 860258 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0718. Min Act: -0.0003

Data Index: 9384 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0719. Min Act: -0.0003

Data Index: 903730 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0725. Min Act: -0.0002

Data Index: 150374 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0715. Min Act: -0.0003

Data Index: 707218 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0699. Min Act: -0.0003

Data Index: 785916 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0700. Min Act: -0.0003

Data Index: 658571 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0686. Min Act: -0.0003

Data Index: 572058 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0696. Min Act: -0.0003

Data Index: 26694 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0675. Min Act: -0.0003

Data Index: 495858 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0672. Min Act: -0.0003

Data Index: 594682 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0684. Min Act: -0.0002

Data Index: 182135 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1033674 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0647. Min Act: -0.0002

Data Index: 907007 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0669. Min Act: -0.0003

Data Index: 874053 (C4 (Web Text))

Max Activating Token Index: 400