Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.9762. Min Act: -0.1700

Data Index: 1526152 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1528806 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1438695 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1406864 (Python Code)

Max Activating Token Index: 586

Text #4

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1440973 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4754. Min Act: -0.1699

Data Index: 1396620 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1493247 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4754. Min Act: -0.1700

Data Index: 1590841 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4127. Min Act: -0.1694

Data Index: 1484513 (Python Code)

Max Activating Token Index: 880

Text #9

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4127. Min Act: -0.1700

Data Index: 1421937 (Python Code)

Max Activating Token Index: 610

Text #10

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4127. Min Act: -0.1700

Data Index: 1424154 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4127. Min Act: -0.1699

Data Index: 1571250 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.4127. Min Act: -0.1700

Data Index: 1530583 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1598359 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1378931 (Python Code)

Max Activating Token Index: 517

Text #15

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1491286 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1451781 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1450378 (Python Code)

Max Activating Token Index: 438

Text #18

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1632969 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 3.9762. Min Range: -3.9762

Max Act: 3.2871. Min Act: -0.1700

Data Index: 1500507 (Python Code)

Max Activating Token Index: 313