Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 515 in Layer 46

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1109. Min Range: -8.1109

Max Act: 8.1109. Min Act: -0.1700

Data Index: 1368935 (Open Web Text)

Max Activating Token Index: 863

Text #1

Max Range: 8.1109. Min Range: -8.1109

Max Act: 8.0796. Min Act: -0.1700

Data Index: 3396601 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 8.1109. Min Range: -8.1109

Max Act: 8.0171. Min Act: -0.1700

Data Index: 2306167 (Open Web Text)

Max Activating Token Index: 842

Text #3

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.7671. Min Act: -0.1700

Data Index: 4204918 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.7359. Min Act: -0.1700

Data Index: 175310 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.7046. Min Act: -0.1700

Data Index: 2133192 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.6734. Min Act: -0.1700

Data Index: 5865391 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.6109. Min Act: -0.1700

Data Index: 8045829 (Open Web Text)

Max Activating Token Index: 748

Text #8

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.5171. Min Act: -0.1700

Data Index: 4950667 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.4859. Min Act: -0.1700

Data Index: 1230229 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.4546. Min Act: -0.1700

Data Index: 6324044 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.4234. Min Act: -0.1700

Data Index: 8593774 (Open Web Text)

Max Activating Token Index: 700

Text #12

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.4234. Min Act: -0.1700

Data Index: 5669939 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.4546. Min Act: -0.1700

Data Index: 167253 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.4234. Min Act: -0.1700

Data Index: 7189466 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.3921. Min Act: -0.1700

Data Index: 2688769 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.3921. Min Act: -0.1700

Data Index: 6546405 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.3921. Min Act: -0.1700

Data Index: 423960 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.3609. Min Act: -0.1700

Data Index: 7673694 (Open Web Text)

Max Activating Token Index: 992

Text #19

Max Range: 8.1109. Min Range: -8.1109

Max Act: 7.3609. Min Act: -0.1700

Data Index: 4874284 (Open Web Text)

Max Activating Token Index: 653