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

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

Neuron 2852 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8977. Min Act: -0.0000

Data Index: 1497063 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7057. Min Act: -0.0000

Data Index: 1612600 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1636555 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1643318 (Python Code)

Max Activating Token Index: 223

Text #4

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1530783 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4497. Min Act: -0.0000

Data Index: 1380282 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4088. Min Act: -0.0000

Data Index: 1642022 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1427091 (Python Code)

Max Activating Token Index: 604

Text #8

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3100. Min Act: -0.0000

Data Index: 1642966 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1503728 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1527402 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1650767 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1492966 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1651149 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1509545 (Python Code)

Max Activating Token Index: 765

Text #15

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1451000 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1560021 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1544524 (Python Code)

Max Activating Token Index: 455

Text #18

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1449797 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1637782 (Python Code)

Max Activating Token Index: 208