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

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

Neuron 1757 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1850. Min Range: -6.1850

Max Act: 6.1850. Min Act: -0.0000

Data Index: 1486977 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.3708. Min Act: -0.0000

Data Index: 1611749 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1896. Min Act: -0.0000

Data Index: 1560007 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.3493. Min Act: -0.0001

Data Index: 1564089 (Python Code)

Max Activating Token Index: 894

Text #4

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.3548. Min Act: -0.0000

Data Index: 1557774 (Python Code)

Max Activating Token Index: 711

Text #5

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.3040. Min Act: -0.0000

Data Index: 1391285 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1940. Min Act: -0.0000

Data Index: 1647076 (Python Code)

Max Activating Token Index: 630

Text #7

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.3349. Min Act: -0.0000

Data Index: 1632677 (Python Code)

Max Activating Token Index: 680

Text #8

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1619. Min Act: -0.0000

Data Index: 1526348 (Python Code)

Max Activating Token Index: 518

Text #9

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1704. Min Act: -0.0000

Data Index: 1640762 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.5321. Min Act: -0.0000

Data Index: 1616131 (Python Code)

Max Activating Token Index: 659

Text #11

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.3397. Min Act: -0.0000

Data Index: 1378011 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1306. Min Act: -0.0000

Data Index: 1373903 (Python Code)

Max Activating Token Index: 642

Text #13

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1681. Min Act: -0.0000

Data Index: 1374925 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.0215. Min Act: -0.0000

Data Index: 1619787 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 6.1850. Min Range: -6.1850

Max Act: 4.8710. Min Act: -0.0000

Data Index: 1646564 (Python Code)

Max Activating Token Index: 597

Text #16

Max Range: 6.1850. Min Range: -6.1850

Max Act: 4.8092. Min Act: -0.0000

Data Index: 1483153 (Python Code)

Max Activating Token Index: 451

Text #17

Max Range: 6.1850. Min Range: -6.1850

Max Act: 5.1348. Min Act: -0.0000

Data Index: 1544785 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 6.1850. Min Range: -6.1850

Max Act: 4.9131. Min Act: -0.0000

Data Index: 1373169 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 6.1850. Min Range: -6.1850

Max Act: 4.7302. Min Act: -0.0000

Data Index: 1434115 (Python Code)

Max Activating Token Index: 542