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

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

Neuron 2896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1425003 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1388129 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1525352 (Python Code)

Max Activating Token Index: 913

Text #3

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1456352 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1499589 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1376472 (Python Code)

Max Activating Token Index: 861

Text #6

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1529461 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1598241 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1540828 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1603867 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1508098 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1535730 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1523669 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1441601 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1621458 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1634908 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1395872 (Python Code)

Max Activating Token Index: 648

Text #17

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1484191 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1386162 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1527796 (Python Code)

Max Activating Token Index: 276