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

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

Neuron 1597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1650891 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1375721 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1529509 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1562237 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1653991 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1444584 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1527836 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1542282 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1656737 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1584137 (Python Code)

Max Activating Token Index: 945

Text #10

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1419255 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1474621 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1467472 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1390232 (Python Code)

Max Activating Token Index: 347

Text #14

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1577149 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1570042 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1377274 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1544770 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1414322 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.9764. Min Range: -0.9764

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1619865 (Python Code)

Max Activating Token Index: 229