Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5556. Min Act: -0.0001

Data Index: 164898 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1416977 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4927. Min Act: -0.0000

Data Index: 792302 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1020358 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1572104 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.3063. Min Act: -0.0001

Data Index: 1546629 (Python Code)

Max Activating Token Index: 1002

Text #6

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.3092. Min Act: -0.0001

Data Index: 1595366 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2642. Min Act: -0.0001

Data Index: 1009049 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2137. Min Act: -0.0001

Data Index: 873603 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2565. Min Act: -0.0001

Data Index: 615237 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.1606. Min Act: -0.0001

Data Index: 1653787 (Python Code)

Max Activating Token Index: 208

Text #11

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2692. Min Act: -0.0001

Data Index: 1578923 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2330. Min Act: -0.0000

Data Index: 1187293 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2702. Min Act: -0.0000

Data Index: 13815 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.0970. Min Act: -0.0000

Data Index: 490253 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.1457. Min Act: -0.0001

Data Index: 1532595 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1459472 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.1547. Min Act: -0.0000

Data Index: 152356 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2538. Min Act: -0.0000

Data Index: 61748 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.5556. Min Range: -1.5556

Max Act: 1.2391. Min Act: -0.0001

Data Index: 260123 (C4 (Web Text))

Max Activating Token Index: 44