Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.5787. Min Act: -0.1700

Data Index: 1454893 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.4850. Min Act: -0.1700

Data Index: 1570121 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.3600. Min Act: -0.1700

Data Index: 1461551 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.3600. Min Act: -0.1700

Data Index: 1361795 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.2662. Min Act: -0.1700

Data Index: 1502710 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.3287. Min Act: -0.1700

Data Index: 1589673 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.2037. Min Act: -0.1700

Data Index: 1534744 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.2350. Min Act: -0.1700

Data Index: 1470763 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.2350. Min Act: -0.1700

Data Index: 1553679 (Python Code)

Max Activating Token Index: 659

Text #9

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.3600. Min Act: -0.1700

Data Index: 1360020 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.2037. Min Act: -0.1700

Data Index: 1370730 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.2037. Min Act: -0.1700

Data Index: 1423442 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1418002 (Python Code)

Max Activating Token Index: 504

Text #13

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1525523 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1400840 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1642648 (Python Code)

Max Activating Token Index: 627

Text #16

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1412. Min Act: -0.1700

Data Index: 1473362 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1529838 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1631967 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 5.5787. Min Range: -5.5787

Max Act: 5.1412. Min Act: -0.1700

Data Index: 1618134 (Python Code)

Max Activating Token Index: 782