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

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

Neuron 4312 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: 2.5047. Min Range: -2.5047

Max Act: 2.5047. Min Act: -0.0000

Data Index: 442603 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.9824. Min Act: -0.0000

Data Index: 1484152 (Python Code)

Max Activating Token Index: 935

Text #2

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.9759. Min Act: -0.0000

Data Index: 1436222 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 2.5047. Min Range: -2.5047

Max Act: 2.0432. Min Act: -0.0000

Data Index: 521795 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.7768. Min Act: -0.0000

Data Index: 1545946 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.7668. Min Act: -0.0000

Data Index: 1613820 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.6476. Min Act: -0.0000

Data Index: 1391514 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.7352. Min Act: -0.0000

Data Index: 396202 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.6188. Min Act: -0.0000

Data Index: 1557070 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1436367 (Python Code)

Max Activating Token Index: 488

Text #10

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.6555. Min Act: -0.0000

Data Index: 1534832 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.7368. Min Act: -0.0000

Data Index: 709830 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1426564 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.5493. Min Act: -0.0000

Data Index: 1600531 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.5582. Min Act: -0.0000

Data Index: 581375 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1091730 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.5665. Min Act: -0.0000

Data Index: 1419299 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1366248 (Python Code)

Max Activating Token Index: 445

Text #18

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.5972. Min Act: -0.0000

Data Index: 1545180 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 2.5047. Min Range: -2.5047

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1524678 (Python Code)

Max Activating Token Index: 513