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

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

Neuron 5732 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.7521. Min Act: -0.0000

Data Index: 128225 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.6829. Min Act: -0.0000

Data Index: 615219 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.6251. Min Act: -0.0000

Data Index: 103437 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1355614 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.6251. Min Act: -0.0000

Data Index: 730303 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.6116. Min Act: -0.0000

Data Index: 434344 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5844. Min Act: -0.0000

Data Index: 656318 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5719. Min Act: -0.0000

Data Index: 73780 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1351301 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1257326 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5283. Min Act: -0.0000

Data Index: 352438 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1226899 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1096560 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5186. Min Act: -0.0000

Data Index: 534091 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5027. Min Act: -0.0000

Data Index: 199665 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5151. Min Act: -0.0000

Data Index: 492261 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5034. Min Act: -0.0000

Data Index: 846614 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5049. Min Act: -0.0000

Data Index: 755118 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4999. Min Act: -0.0000

Data Index: 617828 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4775. Min Act: -0.0000

Data Index: 60087 (C4 (Web Text))

Max Activating Token Index: 180