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

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

Neuron 4937 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: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1469413 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1425647 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1439112 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1574729 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1623302 (Python Code)

Max Activating Token Index: 783

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1600564 (Python Code)

Max Activating Token Index: 942

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1628276 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1615713 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1633375 (Python Code)

Max Activating Token Index: 718

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1457422 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1557859 (Python Code)

Max Activating Token Index: 334

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1570855 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4437. Min Act: -0.0000

Data Index: 591773 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1510469 (Python Code)

Max Activating Token Index: 754

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1647253 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1639666 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1405166 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1410070 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1619378 (Python Code)

Max Activating Token Index: 564

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1562619 (Python Code)

Max Activating Token Index: 418