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

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

Neuron 1145 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1449293 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1376081 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1552892 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1609782 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1381558 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1609669 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1485060 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1406333 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1439528 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1584215 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1588660 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1619512 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1617189 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1555235 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1645789 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1642796 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1557440 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1412038 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1582310 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1459279 (Python Code)

Max Activating Token Index: 3