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

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

Neuron 647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1545871 (Python Code)

Max Activating Token Index: 656

Text #1

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1557842 (Python Code)

Max Activating Token Index: 423

Text #2

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5967. Min Act: -0.0000

Data Index: 564925 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6309. Min Act: -0.0000

Data Index: 430780 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1436771 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1391548 (Python Code)

Max Activating Token Index: 442

Text #6

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1568084 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5706. Min Act: -0.0000

Data Index: 401272 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1565526 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1200212 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5927. Min Act: -0.0000

Data Index: 123599 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1086264 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5194. Min Act: -0.0000

Data Index: 613055 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5496. Min Act: -0.0000

Data Index: 614798 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1413899 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1483653 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1548671 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1588139 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.4974. Min Act: -0.0000

Data Index: 171345 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.6762. Min Range: -0.6762

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1396085 (Python Code)

Max Activating Token Index: 916