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

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

Neuron 4364 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: 6.8954. Min Range: -6.8954

Max Act: 6.8954. Min Act: -0.0000

Data Index: 67447 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.7348. Min Act: -0.0000

Data Index: 428597 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.2419. Min Act: -0.0000

Data Index: 841357 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.3893. Min Act: -0.0000

Data Index: 725049 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.3700. Min Act: -0.0000

Data Index: 824549 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.1840. Min Act: -0.0000

Data Index: 240074 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.2030. Min Act: -0.0000

Data Index: 930502 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.1895. Min Act: -0.0000

Data Index: 1093560 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.0503. Min Act: -0.0000

Data Index: 985539 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 6.8954. Min Range: -6.8954

Max Act: 6.1868. Min Act: -0.0000

Data Index: 1060067 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.7552. Min Act: -0.0000

Data Index: 1147908 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.9391. Min Act: -0.0000

Data Index: 1242605 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.9379. Min Act: 0.0000

Data Index: 39677 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.9122. Min Act: -0.0000

Data Index: 979493 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.8754. Min Act: -0.0000

Data Index: 1167242 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.8702. Min Act: -0.0000

Data Index: 273113 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.8765. Min Act: -0.0000

Data Index: 783690 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.8233. Min Act: -0.0000

Data Index: 971341 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.8018. Min Act: -0.0000

Data Index: 1351751 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 6.8954. Min Range: -6.8954

Max Act: 5.7142. Min Act: -0.0000

Data Index: 1285978 (C4 (Web Text))

Max Activating Token Index: 30