Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 79 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.7018. Min Act: -0.0000

Data Index: 542830 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.6903. Min Act: -0.0000

Data Index: 260343 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.6620. Min Act: -0.0000

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1041390 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.6446. Min Act: -0.0000

Data Index: 204871 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1245945 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.5610. Min Act: -0.0000

Data Index: 233795 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4880. Min Act: -0.0000

Data Index: 911952 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.5668. Min Act: -0.0000

Data Index: 947004 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1039110 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1636204 (Python Code)

Max Activating Token Index: 520

Text #11

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1402136 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4701. Min Act: -0.0000

Data Index: 656198 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1481880 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4715. Min Act: -0.0000

Data Index: 109292 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1379722 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1494462 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1639253 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1534579 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 0.7018. Min Range: -0.7018

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1437667 (Python Code)

Max Activating Token Index: 789