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

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

Neuron 343 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: 0.7309. Min Range: -0.7309

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1547435 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1653587 (Python Code)

Max Activating Token Index: 789

Text #2

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1409895 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1604852 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1430609 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1578327 (Python Code)

Max Activating Token Index: 130

Text #6

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1580478 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1362086 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1529028 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1653995 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1482794 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1650093 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1398902 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1609828 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1611146 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1403197 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1461333 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1565903 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1492052 (Python Code)

Max Activating Token Index: 203

Text #19

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1480742 (Python Code)

Max Activating Token Index: 8