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

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

Neuron 1057 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.8878. Min Act: -0.0001

Data Index: 1512739 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1414407 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.4191. Min Act: -0.0001

Data Index: 1599957 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1573952 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1454008 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.2812. Min Act: -0.0001

Data Index: 1478746 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1365. Min Act: -0.0001

Data Index: 1513915 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1426878 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1639206 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1344. Min Act: -0.0001

Data Index: 1589912 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1447353 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.2002. Min Act: -0.0001

Data Index: 1560456 (Python Code)

Max Activating Token Index: 772

Text #12

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1483729 (Python Code)

Max Activating Token Index: 301

Text #13

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1461351 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1560. Min Act: -0.0001

Data Index: 1537285 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1959. Min Act: -0.0001

Data Index: 1582833 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1394779 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1201. Min Act: -0.0001

Data Index: 1548641 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1320. Min Act: -0.0001

Data Index: 1514744 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 1.8878. Min Range: -1.8878

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1475746 (Python Code)

Max Activating Token Index: 448