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

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

Neuron 940 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.6850. Min Act: -0.1700

Data Index: 703564 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.5600. Min Act: -0.1700

Data Index: 687258 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.5600. Min Act: -0.1700

Data Index: 1031902 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.5287. Min Act: -0.1700

Data Index: 1046866 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3725. Min Act: -0.1700

Data Index: 454573 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.4037. Min Act: -0.1700

Data Index: 289173 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3412. Min Act: -0.1700

Data Index: 931812 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3412. Min Act: -0.1700

Data Index: 876045 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3725. Min Act: -0.1700

Data Index: 289925 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3412. Min Act: -0.1700

Data Index: 1185195 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3412. Min Act: -0.1700

Data Index: 839179 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3100. Min Act: -0.1700

Data Index: 103003 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3100. Min Act: -0.1700

Data Index: 829493 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.2787. Min Act: -0.1700

Data Index: 1343980 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.2475. Min Act: -0.1700

Data Index: 20445 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.2787. Min Act: -0.1700

Data Index: 1287450 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.2475. Min Act: -0.1700

Data Index: 893393 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.1850. Min Act: -0.1700

Data Index: 882908 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.1850. Min Act: -0.1700

Data Index: 1124345 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.1850. Min Act: -0.1700

Data Index: 1109731 (C4 (Web Text))

Max Activating Token Index: 752