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

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

Neuron 2790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1544370 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1135. Min Act: -0.0001

Data Index: 1642549 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1351. Min Act: -0.0001

Data Index: 1360884 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0570. Min Act: -0.0001

Data Index: 1404875 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9895. Min Act: -0.0001

Data Index: 1607851 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0161. Min Act: -0.0001

Data Index: 1532765 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0426. Min Act: -0.0001

Data Index: 1603693 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9723. Min Act: -0.0001

Data Index: 1437396 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0006. Min Act: -0.0001

Data Index: 1646135 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0544. Min Act: -0.0001

Data Index: 1550880 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9908. Min Act: -0.0001

Data Index: 1546967 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1635092 (Python Code)

Max Activating Token Index: 182

Text #12

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1490255 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9682. Min Act: -0.0001

Data Index: 1484134 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1457397 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9425. Min Act: -0.0001

Data Index: 1626359 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1563270 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9742. Min Act: -0.0001

Data Index: 1360368 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1506557 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9904. Min Act: -0.0001

Data Index: 1496466 (Python Code)

Max Activating Token Index: 108