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

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

Neuron 1842 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: 0.8225. Min Range: -0.8225

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1524854 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1258083 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.7511. Min Act: -0.0000

Data Index: 19335 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.7568. Min Act: -0.0000

Data Index: 841513 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.7749. Min Act: -0.0000

Data Index: 634728 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6910. Min Act: -0.0000

Data Index: 778772 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1649219 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6546. Min Act: -0.0000

Data Index: 423137 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6566. Min Act: -0.0000

Data Index: 973125 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1411418 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1632679 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6504. Min Act: -0.0000

Data Index: 817306 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1541771 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1641982 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1570360 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5919. Min Act: -0.0000

Data Index: 878973 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1461335 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1580902 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1492438 (Python Code)

Max Activating Token Index: 810

Text #19

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1290092 (C4 (Web Text))

Max Activating Token Index: 356