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

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

Neuron 4659 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1520586 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1603618 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1569710 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1476001 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1468364 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1581380 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1633707 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1497656 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1481237 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1370612 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1578153 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1525729 (Python Code)

Max Activating Token Index: 137

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1393811 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1399066 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1451919 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1632599 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1570241 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1597547 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1417699 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1562384 (Python Code)

Max Activating Token Index: 20