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

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

Neuron 4663 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0071. Min Range: -2.0071

Max Act: 2.0071. Min Act: -0.0000

Data Index: 843594 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.8656. Min Act: -0.0000

Data Index: 1029984 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.5540. Min Act: -0.0000

Data Index: 286823 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.6299. Min Act: -0.0000

Data Index: 952871 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.2629. Min Act: -0.0000

Data Index: 806362 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.0809. Min Act: -0.0000

Data Index: 387509 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.0273. Min Act: -0.0000

Data Index: 707745 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.0057. Min Act: -0.0000

Data Index: 462426 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1332966 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 2.0071. Min Range: -2.0071

Max Act: 1.0660. Min Act: -0.0000

Data Index: 528900 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9605. Min Act: -0.0000

Data Index: 344596 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9398. Min Act: -0.0000

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9370. Min Act: -0.0000

Data Index: 973630 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9254. Min Act: -0.0000

Data Index: 176144 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9282. Min Act: -0.0000

Data Index: 763127 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9237. Min Act: -0.0000

Data Index: 388767 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1085153 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.8857. Min Act: -0.0000

Data Index: 420235 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9410. Min Act: -0.0000

Data Index: 436589 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 2.0071. Min Range: -2.0071

Max Act: 0.9139. Min Act: -0.0000

Data Index: 941338 (C4 (Web Text))

Max Activating Token Index: 314