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

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

Neuron 3736 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7770. Min Act: -0.0003

Data Index: 852362 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6890. Min Act: -0.0003

Data Index: 1075986 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6820. Min Act: -0.0003

Data Index: 880397 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6396. Min Act: -0.0003

Data Index: 1199543 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6208. Min Act: -0.0003

Data Index: 482804 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6611. Min Act: -0.0003

Data Index: 866072 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6316. Min Act: -0.0003

Data Index: 861684 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6088. Min Act: -0.0002

Data Index: 525054 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6253. Min Act: -0.0002

Data Index: 972239 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6222. Min Act: -0.0003

Data Index: 1108561 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6113. Min Act: -0.0002

Data Index: 658254 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6106. Min Act: -0.0003

Data Index: 855181 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5907. Min Act: -0.0003

Data Index: 507234 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6057. Min Act: -0.0003

Data Index: 840353 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5980. Min Act: -0.0003

Data Index: 11522 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5952. Min Act: -0.0002

Data Index: 455477 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5713. Min Act: -0.0003

Data Index: 1268947 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5899. Min Act: -0.0003

Data Index: 1178093 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5863. Min Act: -0.0003

Data Index: 336156 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5844. Min Act: -0.0003

Data Index: 522743 (C4 (Web Text))

Max Activating Token Index: 537