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

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

Neuron 3098 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9966. Min Act: -0.0000

Data Index: 1548461 (Python Code)

Max Activating Token Index: 761

Text #1

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9742. Min Act: -0.0000

Data Index: 1462130 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9301. Min Act: -0.0000

Data Index: 1604647 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1545024 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0032. Min Act: -0.0000

Data Index: 1598906 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.1430. Min Act: -0.0000

Data Index: 1410780 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.7079. Min Act: -0.0000

Data Index: 1515606 (Python Code)

Max Activating Token Index: 861

Text #7

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.7282. Min Act: -0.0000

Data Index: 1595643 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.8808. Min Act: -0.0000

Data Index: 1609606 (Python Code)

Max Activating Token Index: 697

Text #9

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.8274. Min Act: -0.0000

Data Index: 1612631 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.4635. Min Act: -0.0000

Data Index: 1578943 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.5502. Min Act: -0.0000

Data Index: 1415601 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.5278. Min Act: -0.0000

Data Index: 1644343 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1502158 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.3121. Min Act: -0.0000

Data Index: 1511799 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.2104. Min Act: -0.0000

Data Index: 1398837 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.1225. Min Act: -0.0000

Data Index: 1473086 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.0746. Min Act: -0.0000

Data Index: 1459209 (Python Code)

Max Activating Token Index: 1001

Text #18

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.0294. Min Act: -0.0001

Data Index: 1647462 (Python Code)

Max Activating Token Index: 603

Text #19

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.0154. Min Act: -0.0000

Data Index: 1369977 (Python Code)

Max Activating Token Index: 63