Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1218017 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1648109 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1368088 (Python Code)

Max Activating Token Index: 837

Text #3

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1494136 (Python Code)

Max Activating Token Index: 427

Text #4

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1551738 (Python Code)

Max Activating Token Index: 1002

Text #5

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1517886 (Python Code)

Max Activating Token Index: 445

Text #6

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1378106 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1513022 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1536341 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1638971 (Python Code)

Max Activating Token Index: 105

Text #10

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1619972 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1365841 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1246457 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1539133 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1370443 (Python Code)

Max Activating Token Index: 664

Text #15

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1537659 (Python Code)

Max Activating Token Index: 406

Text #16

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1366001 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1439866 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1501485 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.2577. Min Range: -0.2577

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1491760 (Python Code)

Max Activating Token Index: 328