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

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

Neuron 276 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6903. Min Act: -0.0000

Data Index: 396398 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1348531 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1057320 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1262342 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1544463 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1258682 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1004465 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.6102. Min Act: -0.0000

Data Index: 686035 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5083. Min Act: -0.0000

Data Index: 477453 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5954. Min Act: -0.0000

Data Index: 809163 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5048. Min Act: -0.0000

Data Index: 713822 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5160. Min Act: -0.0000

Data Index: 356495 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1200644 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5147. Min Act: -0.0000

Data Index: 898990 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5047. Min Act: -0.0000

Data Index: 632302 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1230658 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5114. Min Act: -0.0000

Data Index: 221777 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5070. Min Act: -0.0000

Data Index: 691005 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1201510 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1577510 (Python Code)

Max Activating Token Index: 654