Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1412 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.3532. Min Act: -0.1699

Data Index: 1528569 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.3219. Min Act: -0.1700

Data Index: 1268966 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.3219. Min Act: -0.1700

Data Index: 1605495 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.3219. Min Act: -0.1700

Data Index: 414909 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.2907. Min Act: -0.1700

Data Index: 1632732 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1375039 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1344. Min Act: -0.1700

Data Index: 1602738 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1615659 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1969. Min Act: -0.1700

Data Index: 1485195 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1244501 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1524372 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1969. Min Act: -0.1700

Data Index: 620020 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.0719. Min Act: -0.1700

Data Index: 1403068 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1032. Min Act: -0.1700

Data Index: 1384427 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1657. Min Act: -0.1700

Data Index: 1572497 (Python Code)

Max Activating Token Index: 623

Text #15

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.0719. Min Act: -0.1700

Data Index: 1483889 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1032. Min Act: -0.1700

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1344. Min Act: -0.1700

Data Index: 1362400 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1032. Min Act: -0.1700

Data Index: 1529850 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 7.3532. Min Range: -7.3532

Max Act: 7.1032. Min Act: -0.1700

Data Index: 1492952 (Python Code)

Max Activating Token Index: 973