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

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

Neuron 830 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: 5.7844. Min Range: -5.7844

Max Act: 5.7844. Min Act: -0.1700

Data Index: 1402965 (Python Code)

Max Activating Token Index: 652

Text #1

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.7531. Min Act: -0.1700

Data Index: 1613210 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.7531. Min Act: -0.1700

Data Index: 1560623 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6281. Min Act: -0.1700

Data Index: 1372388 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6906. Min Act: -0.1700

Data Index: 1560691 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6594. Min Act: -0.1700

Data Index: 1622642 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6594. Min Act: -0.1700

Data Index: 1486129 (Python Code)

Max Activating Token Index: 935

Text #7

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6594. Min Act: -0.1700

Data Index: 1530133 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6281. Min Act: -0.1700

Data Index: 1369845 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.6281. Min Act: -0.1700

Data Index: 1537760 (Python Code)

Max Activating Token Index: 527

Text #10

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5969. Min Act: -0.1700

Data Index: 1624478 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5969. Min Act: -0.1700

Data Index: 1621397 (Python Code)

Max Activating Token Index: 106

Text #12

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5344. Min Act: -0.1700

Data Index: 1378116 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5344. Min Act: -0.1700

Data Index: 1616911 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5656. Min Act: -0.1700

Data Index: 1548476 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5344. Min Act: -0.1700

Data Index: 1567735 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5344. Min Act: -0.1700

Data Index: 1585615 (Python Code)

Max Activating Token Index: 681

Text #17

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5344. Min Act: -0.1700

Data Index: 1609041 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5031. Min Act: -0.1700

Data Index: 1581965 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 5.7844. Min Range: -5.7844

Max Act: 5.5344. Min Act: -0.1700

Data Index: 1580812 (Python Code)

Max Activating Token Index: 393