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

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

Neuron 92 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.0575. Min Act: -0.0000

Data Index: 1599647 (Python Code)

Max Activating Token Index: 171

Text #1

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.3976. Min Act: -0.0000

Data Index: 1537830 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.3455. Min Act: -0.0000

Data Index: 730498 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.2538. Min Act: -0.0000

Data Index: 1365482 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.8121. Min Act: -0.0000

Data Index: 1561090 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.9465. Min Act: -0.0000

Data Index: 124021 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.0787. Min Act: -0.0000

Data Index: 1449503 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.7113. Min Act: -0.0000

Data Index: 1541432 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.0720. Min Act: -0.0000

Data Index: 1368782 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.0879. Min Act: -0.0000

Data Index: 1542121 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.8915. Min Act: -0.0000

Data Index: 1084987 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 6.3976. Min Range: -6.3976

Max Act: 6.0018. Min Act: -0.0000

Data Index: 1329895 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.7215. Min Act: -0.0000

Data Index: 995322 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.5562. Min Act: -0.0000

Data Index: 1346707 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.9470. Min Act: -0.0000

Data Index: 1411384 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.5423. Min Act: -0.0000

Data Index: 1561442 (Python Code)

Max Activating Token Index: 761

Text #16

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.6477. Min Act: -0.0000

Data Index: 1397854 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.9303. Min Act: -0.0000

Data Index: 1409145 (Python Code)

Max Activating Token Index: 811

Text #18

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.3536. Min Act: -0.0000

Data Index: 1612480 (Python Code)

Max Activating Token Index: 999

Text #19

Max Range: 6.3976. Min Range: -6.3976

Max Act: 5.7430. Min Act: -0.0000

Data Index: 1547406 (Python Code)

Max Activating Token Index: 149