Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2396. Min Act: -0.0002

Data Index: 1456381 (Python Code)

Max Activating Token Index: 228

Text #1

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2241. Min Act: -0.0002

Data Index: 1619877 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2143. Min Act: -0.0002

Data Index: 1455396 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1439403 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2122. Min Act: -0.0002

Data Index: 1609248 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2058. Min Act: -0.0002

Data Index: 1462383 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2117. Min Act: -0.0002

Data Index: 1398358 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1998. Min Act: -0.0002

Data Index: 1488693 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2017. Min Act: -0.0002

Data Index: 1379378 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2134. Min Act: -0.0002

Data Index: 1549724 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1425787 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2006. Min Act: -0.0002

Data Index: 1648403 (Python Code)

Max Activating Token Index: 719

Text #12

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2014. Min Act: -0.0002

Data Index: 1472580 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1649304 (Python Code)

Max Activating Token Index: 882

Text #14

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1505251 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2004. Min Act: -0.0002

Data Index: 1456435 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1970. Min Act: -0.0002

Data Index: 1461297 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.2023. Min Act: -0.0002

Data Index: 1585536 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1910. Min Act: -0.0002

Data Index: 1389479 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 0.2396. Min Range: -0.2396

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1364743 (Python Code)

Max Activating Token Index: 825