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

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

Neuron 1099 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2679. Min Range: -8.2679

Max Act: 8.2679. Min Act: -0.1700

Data Index: 1625439 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 8.2679. Min Range: -8.2679

Max Act: 8.0804. Min Act: -0.1700

Data Index: 1481213 (Python Code)

Max Activating Token Index: 131

Text #2

Max Range: 8.2679. Min Range: -8.2679

Max Act: 8.0491. Min Act: -0.1700

Data Index: 1446675 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 8.2679. Min Range: -8.2679

Max Act: 8.0804. Min Act: -0.1700

Data Index: 1514929 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.9554. Min Act: -0.1700

Data Index: 1523388 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 8.2679. Min Range: -8.2679

Max Act: 8.0179. Min Act: -0.1700

Data Index: 1654079 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.9866. Min Act: -0.1700

Data Index: 1588946 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.9866. Min Act: -0.1700

Data Index: 1475653 (Python Code)

Max Activating Token Index: 755

Text #8

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.9241. Min Act: -0.1700

Data Index: 1402575 (Python Code)

Max Activating Token Index: 873

Text #9

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8616. Min Act: -0.1700

Data Index: 1609654 (Python Code)

Max Activating Token Index: 403

Text #10

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8929. Min Act: -0.1700

Data Index: 1449022 (Python Code)

Max Activating Token Index: 271

Text #11

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8929. Min Act: -0.1700

Data Index: 1362750 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8304. Min Act: -0.1700

Data Index: 1461715 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.9241. Min Act: -0.1700

Data Index: 1497466 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8616. Min Act: -0.1700

Data Index: 1652466 (Python Code)

Max Activating Token Index: 980

Text #15

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.9241. Min Act: -0.1700

Data Index: 1442014 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8616. Min Act: -0.1700

Data Index: 1411534 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8616. Min Act: -0.1700

Data Index: 1576018 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8304. Min Act: -0.1700

Data Index: 1503944 (Python Code)

Max Activating Token Index: 691

Text #19

Max Range: 8.2679. Min Range: -8.2679

Max Act: 7.8616. Min Act: -0.1700

Data Index: 1447629 (Python Code)

Max Activating Token Index: 142