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

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

Neuron 2979 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8819. Min Act: -0.0002

Data Index: 545169 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8534. Min Act: -0.0003

Data Index: 881765 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8056. Min Act: -0.0002

Data Index: 1268626 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7976. Min Act: -0.0002

Data Index: 571588 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8222. Min Act: -0.0002

Data Index: 96670 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7846. Min Act: -0.0002

Data Index: 1080254 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7871. Min Act: -0.0002

Data Index: 43402 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7828. Min Act: -0.0002

Data Index: 450659 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7745. Min Act: -0.0002

Data Index: 204887 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7598. Min Act: -0.0002

Data Index: 986043 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7564. Min Act: -0.0002

Data Index: 772371 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7606. Min Act: -0.0002

Data Index: 282831 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7607. Min Act: -0.0002

Data Index: 472619 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7442. Min Act: -0.0002

Data Index: 76056 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7375. Min Act: -0.0002

Data Index: 290344 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7250. Min Act: -0.0002

Data Index: 211250 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7124. Min Act: -0.0002

Data Index: 1299658 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7331. Min Act: -0.0002

Data Index: 274769 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7227. Min Act: -0.0002

Data Index: 179967 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7164. Min Act: -0.0002

Data Index: 869768 (C4 (Web Text))

Max Activating Token Index: 36