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

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

Neuron 815 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0910. Min Range: -3.0910

Max Act: 3.0910. Min Act: -0.0000

Data Index: 565108 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.6846. Min Act: -0.0000

Data Index: 1161131 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8945. Min Act: -0.0000

Data Index: 211493 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8086. Min Act: -0.0000

Data Index: 649439 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.5213. Min Act: -0.0000

Data Index: 186925 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.4631. Min Act: -0.0000

Data Index: 843072 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.3673. Min Act: -0.0000

Data Index: 193908 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.1534. Min Act: -0.0000

Data Index: 871531 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.2086. Min Act: -0.0000

Data Index: 711143 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.2954. Min Act: -0.0000

Data Index: 997660 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 3.0910. Min Range: -3.0910

Max Act: 1.9135. Min Act: -0.0000

Data Index: 791441 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.2359. Min Act: -0.0000

Data Index: 500866 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.1990. Min Act: -0.0000

Data Index: 73141 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 3.0910. Min Range: -3.0910

Max Act: 1.8476. Min Act: -0.0000

Data Index: 21060 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.0711. Min Act: -0.0000

Data Index: 1049313 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.2982. Min Act: -0.0000

Data Index: 544267 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.1734. Min Act: -0.0000

Data Index: 845170 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.0394. Min Act: -0.0000

Data Index: 696396 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.1655. Min Act: -0.0000

Data Index: 595631 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 3.0910. Min Range: -3.0910

Max Act: 1.7909. Min Act: -0.0000

Data Index: 519739 (C4 (Web Text))

Max Activating Token Index: 532