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

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

Neuron 1591 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: 2.2736. Min Range: -2.2736

Max Act: 2.2736. Min Act: -0.0000

Data Index: 1619516 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9798. Min Act: -0.0000

Data Index: 1631035 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.0870. Min Act: -0.0000

Data Index: 1500068 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9967. Min Act: -0.0000

Data Index: 1392763 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.8786. Min Act: -0.0000

Data Index: 1618694 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1501556 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9759. Min Act: -0.0000

Data Index: 1567363 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9673. Min Act: -0.0000

Data Index: 1510041 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9673. Min Act: -0.0000

Data Index: 1411211 (Python Code)

Max Activating Token Index: 39

Text #9

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9764. Min Act: -0.0000

Data Index: 1556798 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9714. Min Act: -0.0000

Data Index: 1497733 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9668. Min Act: -0.0000

Data Index: 1446324 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.8506. Min Act: -0.0000

Data Index: 1477566 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1561330 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9566. Min Act: -0.0000

Data Index: 1528167 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1394302 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1387680 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.8110. Min Act: -0.0000

Data Index: 1581934 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.9973. Min Act: -0.0000

Data Index: 1379439 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 2.2736. Min Range: -2.2736

Max Act: 1.7890. Min Act: -0.0000

Data Index: 1616339 (Python Code)

Max Activating Token Index: 30