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

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

Neuron 357 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8789. Min Act: -0.1700

Data Index: 236611 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8320. Min Act: -0.1700

Data Index: 212034 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8632. Min Act: -0.1700

Data Index: 728265 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8163. Min Act: -0.1700

Data Index: 532705 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8007. Min Act: -0.1700

Data Index: 942829 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7850. Min Act: -0.1700

Data Index: 772328 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8007. Min Act: -0.1700

Data Index: 1192729 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.8007. Min Act: -0.1700

Data Index: 1276171 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7537. Min Act: -0.1700

Data Index: 976219 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7537. Min Act: -0.1700

Data Index: 165475 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7537. Min Act: -0.1700

Data Index: 630202 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7381. Min Act: -0.1700

Data Index: 1352255 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7537. Min Act: -0.1700

Data Index: 724198 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7537. Min Act: -0.1700

Data Index: 836069 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7225. Min Act: -0.1700

Data Index: 763049 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7225. Min Act: -0.1700

Data Index: 1252468 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7381. Min Act: -0.1700

Data Index: 650340 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7068. Min Act: -0.1700

Data Index: 732583 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7225. Min Act: -0.1700

Data Index: 354902 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7537. Min Act: -0.1700

Data Index: 651426 (C4 (Web Text))

Max Activating Token Index: 739