Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 2175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.1109. Min Act: -0.1700

Data Index: 688466 (Open Web Text)

Max Activating Token Index: 573

Text #1

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0796. Min Act: -0.1700

Data Index: 7295010 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.0484. Min Act: -0.1700

Data Index: 5501215 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9859. Min Act: -0.1700

Data Index: 2801433 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 7443849 (Open Web Text)

Max Activating Token Index: 292

Text #5

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1695

Data Index: 1876999 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1642

Data Index: 4567825 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 8036511 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 2428615 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 4392280 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 7972354 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1699

Data Index: 4018699 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 7660610 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 4737903 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 332339 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 2713009 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1687

Data Index: 2671353 (Open Web Text)

Max Activating Token Index: 949

Text #17

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1694

Data Index: 7054104 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9546. Min Act: -0.1700

Data Index: 5071697 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1700

Data Index: 5549387 (Open Web Text)

Max Activating Token Index: 505