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

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

Neuron 1538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1612770 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9376. Min Act: -0.1700

Data Index: 1621155 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1374094 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1427776 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1552954 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1501051 (Python Code)

Max Activating Token Index: 686

Text #6

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8595. Min Act: -0.1700

Data Index: 1546484 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1534946 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1421331 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1449099 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1482866 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1511708 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1508158 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8751. Min Act: -0.1700

Data Index: 1600850 (Python Code)

Max Activating Token Index: 449

Text #14

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1499235 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1491443 (Python Code)

Max Activating Token Index: 521

Text #16

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1410794 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8907. Min Act: -0.1700

Data Index: 1435157 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8595. Min Act: -0.1700

Data Index: 1516727 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8751. Min Act: -0.1700

Data Index: 1608655 (Python Code)

Max Activating Token Index: 632