Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2687 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.9037. Min Act: -0.0000

Data Index: 706427 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1906007 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1588395 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7999. Min Act: -0.0000

Data Index: 918580 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7655. Min Act: -0.0000

Data Index: 500313 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7983. Min Act: -0.0000

Data Index: 252802 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7459. Min Act: -0.0000

Data Index: 326148 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1460234 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1596503 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1494161 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7484. Min Act: -0.0000

Data Index: 372828 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1383977 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1895382 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1239726 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1824364 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1131015 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1143003 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1821756 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1560003 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1895309 (The Pile)

Max Activating Token Index: 658