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

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

Neuron 3509 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: 0.7320. Min Range: -0.7320

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1230816 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1037685 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.7229. Min Act: -0.0000

Data Index: 600389 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.7320. Min Act: -0.0000

Data Index: 26936 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6359. Min Act: -0.0000

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.6120. Min Act: 0.0000

Data Index: 946043 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1057340 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5863. Min Act: -0.0000

Data Index: 788944 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5440. Min Act: -0.0000

Data Index: 925571 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5655. Min Act: -0.0000

Data Index: 291216 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1111178 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4690. Min Act: -0.0000

Data Index: 276532 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5051. Min Act: -0.0000

Data Index: 53275 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4139. Min Act: -0.0000

Data Index: 143055 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4760. Min Act: -0.0000

Data Index: 489085 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4453. Min Act: -0.0000

Data Index: 211353 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4529. Min Act: -0.0000

Data Index: 766251 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.5031. Min Act: -0.0000

Data Index: 478860 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.7320. Min Range: -0.7320

Max Act: 0.4469. Min Act: -0.0000

Data Index: 895123 (C4 (Web Text))

Max Activating Token Index: 370