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

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

Neuron 1507 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1636596 (Python Code)

Max Activating Token Index: 832

Text #1

Max Range: 1.3861. Min Range: -1.3861

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1492077 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1462959 (Python Code)

Max Activating Token Index: 913

Text #3

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1532595 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1401661 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9351. Min Act: 0.0000

Data Index: 1443949 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1451977 (Python Code)

Max Activating Token Index: 466

Text #7

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1624849 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1534060 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1489127 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1402863 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1646402 (Python Code)

Max Activating Token Index: 1000

Text #12

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1587167 (Python Code)

Max Activating Token Index: 344

Text #13

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1627324 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1383370 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1412265 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1500308 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1486467 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1553821 (Python Code)

Max Activating Token Index: 171

Text #19

Max Range: 1.3861. Min Range: -1.3861

Max Act: 0.8153. Min Act: 0.0000

Data Index: 1447914 (Python Code)

Max Activating Token Index: 122