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

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

Neuron 1973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1885. Min Range: -4.1885

Max Act: 4.1885. Min Act: -0.0000

Data Index: 85439 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 4.1885. Min Range: -4.1885

Max Act: 4.0708. Min Act: -0.0000

Data Index: 1029561 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.7157. Min Act: -0.0000

Data Index: 40566 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.5812. Min Act: -0.0000

Data Index: 833285 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.4858. Min Act: -0.0000

Data Index: 158925 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.3585. Min Act: -0.0000

Data Index: 1168706 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.1831. Min Act: -0.0000

Data Index: 192804 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.3102. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.2442. Min Act: -0.0000

Data Index: 623013 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 4.1885. Min Range: -4.1885

Max Act: 2.9457. Min Act: -0.0000

Data Index: 724060 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.0172. Min Act: -0.0000

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.1150. Min Act: -0.0000

Data Index: 18727 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.4381. Min Act: -0.0000

Data Index: 876579 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 4.1885. Min Range: -4.1885

Max Act: 2.8988. Min Act: -0.0000

Data Index: 228441 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.0178. Min Act: -0.0000

Data Index: 305317 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 4.1885. Min Range: -4.1885

Max Act: 3.0263. Min Act: -0.0000

Data Index: 1312636 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 4.1885. Min Range: -4.1885

Max Act: 2.9895. Min Act: -0.0000

Data Index: 537482 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 4.1885. Min Range: -4.1885

Max Act: 2.9778. Min Act: -0.0000

Data Index: 18936 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 4.1885. Min Range: -4.1885

Max Act: 2.8308. Min Act: -0.0000

Data Index: 124117 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 4.1885. Min Range: -4.1885

Max Act: 2.8057. Min Act: -0.0000

Data Index: 1006366 (C4 (Web Text))

Max Activating Token Index: 777