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

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

Neuron 1840 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: 3.6142. Min Range: -3.6142

Max Act: 3.6142. Min Act: -0.1700

Data Index: 1390830 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.5202. Min Act: -0.1700

Data Index: 1539815 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4889. Min Act: -0.1700

Data Index: 1381323 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4889. Min Act: -0.1700

Data Index: 1468642 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4889. Min Act: -0.1700

Data Index: 1464650 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4575. Min Act: -0.1700

Data Index: 1367049 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4262. Min Act: -0.1700

Data Index: 1420505 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4262. Min Act: -0.1700

Data Index: 1606601 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4262. Min Act: -0.1700

Data Index: 1627836 (Python Code)

Max Activating Token Index: 179

Text #9

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.4262. Min Act: -0.1700

Data Index: 1588921 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1473060 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1518218 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1460795 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1461956 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1584468 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1515699 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1554465 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1446505 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1449854 (Python Code)

Max Activating Token Index: 450

Text #19

Max Range: 3.6142. Min Range: -3.6142

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1547253 (Python Code)

Max Activating Token Index: 131