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

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

Neuron 1637 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.7251. Min Act: -0.0000

Data Index: 649299 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6747. Min Act: -0.0000

Data Index: 743312 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1322852 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.5347. Min Act: -0.0000

Data Index: 178613 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1025814 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4814. Min Act: -0.0000

Data Index: 122012 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4392. Min Act: -0.0000

Data Index: 210038 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1410429 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1480680 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3832. Min Act: -0.0000

Data Index: 102980 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3816. Min Act: -0.0000

Data Index: 297162 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1520890 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3810. Min Act: -0.0000

Data Index: 815515 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1587047 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1592441 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3649. Min Act: -0.0000

Data Index: 734488 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1625767 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1454153 (Python Code)

Max Activating Token Index: 936

Text #19

Max Range: 0.7251. Min Range: -0.7251

Max Act: 0.3610. Min Act: -0.0000

Data Index: 14786 (C4 (Web Text))

Max Activating Token Index: 301