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

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

Neuron 947 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1091869 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8520. Min Act: -0.0000

Data Index: 574121 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.8313. Min Act: -0.0000

Data Index: 823680 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.7196. Min Act: -0.0000

Data Index: 196427 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.6897. Min Act: -0.0000

Data Index: 984036 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.6358. Min Act: -0.0000

Data Index: 98039 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.6189. Min Act: -0.0000

Data Index: 586956 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5074. Min Act: -0.0000

Data Index: 881561 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4274. Min Act: -0.0000

Data Index: 199549 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4104. Min Act: -0.0000

Data Index: 566281 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3933. Min Act: -0.0000

Data Index: 277973 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3919. Min Act: -0.0000

Data Index: 272150 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4028. Min Act: -0.0000

Data Index: 806000 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4030. Min Act: -0.0000

Data Index: 961465 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3776. Min Act: -0.0000

Data Index: 808417 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3650. Min Act: -0.0000

Data Index: 171836 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3581. Min Act: -0.0000

Data Index: 655767 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3572. Min Act: -0.0000

Data Index: 64547 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1144465 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.3465. Min Act: -0.0000

Data Index: 31091 (C4 (Web Text))

Max Activating Token Index: 483