Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1737 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.9950. Min Act: -0.1699

Data Index: 1394293 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.9012. Min Act: -0.1699

Data Index: 1605798 (Python Code)

Max Activating Token Index: 621

Text #2

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.9012. Min Act: -0.1700

Data Index: 1368687 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8387. Min Act: -0.1700

Data Index: 1649862 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1489730 (Python Code)

Max Activating Token Index: 731

Text #5

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1451658 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1699

Data Index: 1452462 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8387. Min Act: -0.1699

Data Index: 1405614 (Python Code)

Max Activating Token Index: 658

Text #8

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1527559 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1699

Data Index: 1474532 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1488124 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1368996 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1371070 (Python Code)

Max Activating Token Index: 64

Text #13

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.7761. Min Act: -0.1700

Data Index: 1456127 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1456663 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1620026 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1463552 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1487742 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1566858 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1426083 (Python Code)

Max Activating Token Index: 272