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

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

Neuron 5291 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: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0000

Data Index: 854294 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1200276 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1290744 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1862. Min Act: -0.0000

Data Index: 947733 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1922. Min Act: -0.0000

Data Index: 282743 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1125391 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1910. Min Act: -0.0000

Data Index: 376566 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1865. Min Act: -0.0000

Data Index: 981751 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1930. Min Act: -0.0000

Data Index: 744088 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1793. Min Act: -0.0000

Data Index: 672324 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1134238 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1824. Min Act: -0.0000

Data Index: 51631 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1922. Min Act: -0.0000

Data Index: 183226 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1722. Min Act: -0.0000

Data Index: 590244 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1294079 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1708. Min Act: -0.0000

Data Index: 330905 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1649. Min Act: -0.0000

Data Index: 382625 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1633. Min Act: -0.0000

Data Index: 176524 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1673. Min Act: -0.0000

Data Index: 796122 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1131438 (C4 (Web Text))

Max Activating Token Index: 327