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

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

Neuron 3370 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1372856 (Python Code)

Max Activating Token Index: 800

Text #1

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1497177 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1524126 (Python Code)

Max Activating Token Index: 846

Text #3

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1428245 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1618883 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1520380 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1565194 (Python Code)

Max Activating Token Index: 547

Text #7

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1654817 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1452907 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1592663 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1368787 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1527975 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1452869 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1629892 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1426726 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1463791 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1587340 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1453914 (Python Code)

Max Activating Token Index: 549

Text #18

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1442848 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1644201 (Python Code)

Max Activating Token Index: 182