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

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

Neuron 6046 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2600. Min Range: -1.2600

Max Act: 1.2600. Min Act: -0.0001

Data Index: 1401321 (Python Code)

Max Activating Token Index: 207

Text #1

Max Range: 1.2600. Min Range: -1.2600

Max Act: 1.1835. Min Act: -0.0001

Data Index: 1531018 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 1.2600. Min Range: -1.2600

Max Act: 1.0417. Min Act: -0.0001

Data Index: 1566963 (Python Code)

Max Activating Token Index: 8

Text #3

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9068. Min Act: -0.0001

Data Index: 1654040 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1577999 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1633879 (Python Code)

Max Activating Token Index: 630

Text #6

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1370311 (Python Code)

Max Activating Token Index: 976

Text #7

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8299. Min Act: -0.0001

Data Index: 1045834 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8215. Min Act: -0.0001

Data Index: 1362192 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8442. Min Act: -0.0001

Data Index: 1535279 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1561073 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7741. Min Act: -0.0001

Data Index: 1399441 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1433024 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1503820 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7038. Min Act: -0.0001

Data Index: 1377066 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1396883 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7452. Min Act: -0.0001

Data Index: 1646003 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1529132 (Python Code)

Max Activating Token Index: 457

Text #18

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7006. Min Act: -0.0001

Data Index: 1544554 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1539508 (Python Code)

Max Activating Token Index: 246