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

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

Neuron 1235 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: 1.8976. Min Range: -1.8976

Max Act: 1.8976. Min Act: -0.0000

Data Index: 1615376 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.7274. Min Act: -0.0000

Data Index: 1638335 (Python Code)

Max Activating Token Index: 992

Text #2

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.5844. Min Act: -0.0000

Data Index: 1507093 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1612821 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.6321. Min Act: -0.0000

Data Index: 1619280 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.6708. Min Act: -0.0000

Data Index: 1372534 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1568746 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1517866 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1463739 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1650020 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1585993 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1522784 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1362692 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1428048 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4795. Min Act: -0.0000

Data Index: 1454653 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1501026 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1524968 (Python Code)

Max Activating Token Index: 690

Text #17

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1450673 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1444928 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 1.8976. Min Range: -1.8976

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1635803 (Python Code)

Max Activating Token Index: 967