Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 11 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0598. Min Act: -0.0004

Data Index: 877703 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1233614 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1352806 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1009893 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0524. Min Act: -0.0003

Data Index: 733697 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1432542 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0503. Min Act: -0.0003

Data Index: 950025 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0513. Min Act: -0.0003

Data Index: 599754 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1441400 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0482. Min Act: -0.0003

Data Index: 557345 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0510. Min Act: -0.0003

Data Index: 395592 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0478. Min Act: -0.0004

Data Index: 1289205 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0476. Min Act: -0.0003

Data Index: 229454 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0466. Min Act: -0.0003

Data Index: 954590 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0483. Min Act: -0.0003

Data Index: 192144 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1289739 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1217076 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0467. Min Act: -0.0003

Data Index: 695107 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0490. Min Act: -0.0003

Data Index: 603771 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1524778 (Python Code)

Max Activating Token Index: 576