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

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

Neuron 2585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1460635 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1447688 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1562919 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1411799 (Python Code)

Max Activating Token Index: 424

Text #4

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1465494 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1396944 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1421366 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1639496 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1645651 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1509511 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1432994 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1507209 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1368510 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1608847 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1446333 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1392324 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1457490 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1560395 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1494287 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.8607. Min Range: -0.8607

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1414669 (Python Code)

Max Activating Token Index: 7