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

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

Neuron 3336 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1623738 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1489867 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1612734 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9373. Min Act: 0.0000

Data Index: 1494020 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.8115. Min Act: 0.0000

Data Index: 1379936 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.7330. Min Act: 0.0000

Data Index: 1619594 (Python Code)

Max Activating Token Index: 593

Text #6

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.7768. Min Act: 0.0001

Data Index: 1382970 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.7376. Min Act: 0.0001

Data Index: 1507351 (Python Code)

Max Activating Token Index: 185

Text #8

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1436881 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6742. Min Act: 0.0001

Data Index: 1382653 (Python Code)

Max Activating Token Index: 842

Text #10

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6635. Min Act: 0.0000

Data Index: 1582438 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6847. Min Act: 0.0000

Data Index: 1582357 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1465767 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6624. Min Act: 0.0001

Data Index: 1501835 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6440. Min Act: 0.0000

Data Index: 1440529 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1650279 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6134. Min Act: 0.0000

Data Index: 1469936 (Python Code)

Max Activating Token Index: 393

Text #17

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1474253 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.5744. Min Act: 0.0000

Data Index: 1411357 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1580715 (Python Code)

Max Activating Token Index: 1013