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

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

Neuron 1935 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: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1501794 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1502734 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1451386 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1548006 (Python Code)

Max Activating Token Index: 758

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1490210 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1434074 (Python Code)

Max Activating Token Index: 397

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1368370 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1454241 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1586945 (Python Code)

Max Activating Token Index: 473

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1517883 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1468461 (Python Code)

Max Activating Token Index: 319

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1495857 (Python Code)

Max Activating Token Index: 264

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1446311 (Python Code)

Max Activating Token Index: 738

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1640918 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1487616 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0841. Min Act: -0.0001

Data Index: 579219 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1435329 (Python Code)

Max Activating Token Index: 429

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1620673 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1471121 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1427538 (Python Code)

Max Activating Token Index: 765