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

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

Neuron 2006 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.5156. Min Act: -0.1700

Data Index: 1365765 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4999. Min Act: -0.1700

Data Index: 1544284 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4843. Min Act: -0.1700

Data Index: 1385126 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1418905 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4686. Min Act: -0.1700

Data Index: 1651236 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1425030 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4529. Min Act: -0.1700

Data Index: 1564859 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4686. Min Act: -0.1700

Data Index: 1535060 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1561891 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4216. Min Act: -0.1700

Data Index: 1611992 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1380321 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1395623 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1553075 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4372. Min Act: -0.1700

Data Index: 1553448 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4216. Min Act: -0.1700

Data Index: 1365430 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4216. Min Act: -0.1700

Data Index: 1446784 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4216. Min Act: -0.1700

Data Index: 1406838 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.3902. Min Act: -0.1700

Data Index: 1610909 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.4059. Min Act: -0.1700

Data Index: 1556689 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 3.5156. Min Range: -3.5156

Max Act: 3.3902. Min Act: -0.1700

Data Index: 1583456 (Python Code)

Max Activating Token Index: 144