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

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

Neuron 1564 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8429. Min Act: -0.0000

Data Index: 16765 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1328550 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8589. Min Act: -0.0000

Data Index: 261782 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1203286 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7702. Min Act: -0.0000

Data Index: 276841 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7537. Min Act: -0.0000

Data Index: 179426 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7244. Min Act: -0.0000

Data Index: 735000 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7118. Min Act: -0.0000

Data Index: 877166 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7333. Min Act: -0.0000

Data Index: 701214 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7057. Min Act: -0.0000

Data Index: 897249 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7200. Min Act: -0.0000

Data Index: 598945 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7023. Min Act: -0.0000

Data Index: 695967 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1142629 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6917. Min Act: -0.0000

Data Index: 739615 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6873. Min Act: -0.0000

Data Index: 890235 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7006. Min Act: -0.0000

Data Index: 604695 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1136110 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6532. Min Act: -0.0000

Data Index: 149428 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6695. Min Act: -0.0000

Data Index: 872250 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1066899 (C4 (Web Text))

Max Activating Token Index: 446