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

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

Neuron 88 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: 6.1837. Min Range: -6.1837

Max Act: 5.8140. Min Act: -0.0000

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 6.1837. Min Range: -6.1837

Max Act: 6.0508. Min Act: -0.0000

Data Index: 809781 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.9945. Min Act: -0.0000

Data Index: 650716 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.6596. Min Act: -0.0000

Data Index: 986994 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 6.1837. Min Range: -6.1837

Max Act: 6.1837. Min Act: -0.0000

Data Index: 1141283 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.6023. Min Act: -0.0000

Data Index: 151810 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.7685. Min Act: -0.0000

Data Index: 351239 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.9096. Min Act: -0.0000

Data Index: 307080 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.5401. Min Act: -0.0000

Data Index: 1025342 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.5973. Min Act: -0.0000

Data Index: 882316 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.3974. Min Act: -0.0000

Data Index: 317218 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.3372. Min Act: -0.0000

Data Index: 926323 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.5187. Min Act: -0.0000

Data Index: 400540 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.5122. Min Act: -0.0000

Data Index: 248925 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.6933. Min Act: -0.0000

Data Index: 421724 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.1295. Min Act: -0.0001

Data Index: 220066 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.5063. Min Act: -0.0000

Data Index: 1006834 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.4853. Min Act: -0.0000

Data Index: 351415 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.2286. Min Act: -0.0000

Data Index: 68687 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 6.1837. Min Range: -6.1837

Max Act: 5.0427. Min Act: -0.0000

Data Index: 1080515 (C4 (Web Text))

Max Activating Token Index: 30