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

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

Neuron 84 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: 1.7136. Min Range: -1.7136

Max Act: 1.7136. Min Act: -0.0000

Data Index: 1386289 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 1.7136. Min Range: -1.7136

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1414699 (Python Code)

Max Activating Token Index: 426

Text #2

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1618633 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1473925 (Python Code)

Max Activating Token Index: 855

Text #4

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.8001. Min Act: -0.0000

Data Index: 370132 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1600336 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1393159 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1604686 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1515479 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1575049 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1632586 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1642790 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1639855 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1429348 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1524014 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1465133 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1569655 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1487564 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1609304 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 1.7136. Min Range: -1.7136

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1591875 (Python Code)

Max Activating Token Index: 924