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

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

Neuron 4980 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.5180. Min Act: -0.0000

Data Index: 276149 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.7504. Min Act: -0.0000

Data Index: 76151 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.1720. Min Act: -0.0000

Data Index: 581619 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.4440. Min Act: -0.0000

Data Index: 250611 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.2231. Min Act: -0.0000

Data Index: 1049251 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.2823. Min Act: -0.0000

Data Index: 1058443 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.2486. Min Act: -0.0000

Data Index: 809421 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.5731. Min Act: -0.0000

Data Index: 245673 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 4.7504. Min Range: -4.7504

Max Act: 3.8934. Min Act: -0.0000

Data Index: 123112 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.0507. Min Act: -0.0000

Data Index: 467410 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.0284. Min Act: -0.0000

Data Index: 54223 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.2056. Min Act: -0.0000

Data Index: 861213 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.0354. Min Act: -0.0000

Data Index: 150514 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.1892. Min Act: -0.0000

Data Index: 750286 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 4.7504. Min Range: -4.7504

Max Act: 3.7999. Min Act: -0.0000

Data Index: 591523 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.0875. Min Act: -0.0000

Data Index: 445015 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 4.7504. Min Range: -4.7504

Max Act: 3.8808. Min Act: -0.0000

Data Index: 1292826 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.0322. Min Act: -0.0000

Data Index: 1158227 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 4.7504. Min Range: -4.7504

Max Act: 4.0099. Min Act: -0.0000

Data Index: 403787 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 4.7504. Min Range: -4.7504

Max Act: 3.9724. Min Act: -0.0000

Data Index: 972283 (C4 (Web Text))

Max Activating Token Index: 809