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

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

Neuron 1703 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: 3.5193. Min Range: -3.5193

Max Act: 3.5193. Min Act: -0.1700

Data Index: 1451543 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.5193. Min Act: -0.1700

Data Index: 1448944 (Python Code)

Max Activating Token Index: 599

Text #2

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1420764 (Python Code)

Max Activating Token Index: 85

Text #3

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1552790 (Python Code)

Max Activating Token Index: 165

Text #4

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1492988 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4566. Min Act: -0.1700

Data Index: 63173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1363268 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4096. Min Act: -0.1700

Data Index: 1383928 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3939. Min Act: -0.1700

Data Index: 1361272 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1396873 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4096. Min Act: -0.1700

Data Index: 1564952 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1459890 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1610743 (Python Code)

Max Activating Token Index: 207

Text #13

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3939. Min Act: -0.1700

Data Index: 1375087 (Python Code)

Max Activating Token Index: 873

Text #14

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3782. Min Act: -0.1700

Data Index: 1646849 (Python Code)

Max Activating Token Index: 886

Text #15

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3782. Min Act: -0.1700

Data Index: 1456444 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1487627 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3782. Min Act: -0.1700

Data Index: 1601207 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3782. Min Act: -0.1700

Data Index: 563188 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 3.5193. Min Range: -3.5193

Max Act: 3.3782. Min Act: -0.1700

Data Index: 113051 (C4 (Web Text))

Max Activating Token Index: 1023