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

Dataset: Open Web Text

Neuron 3765 in Layer 27

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1109. Min Range: -5.1109

Max Act: 5.1109. Min Act: -0.1700

Data Index: 7887851 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7046. Min Act: -0.1700

Data Index: 2851262 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7046. Min Act: -0.1700

Data Index: 3234694 (Open Web Text)

Max Activating Token Index: 449

Text #3

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7046. Min Act: -0.1700

Data Index: 4545665 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5484. Min Act: -0.1700

Data Index: 5921263 (Open Web Text)

Max Activating Token Index: 833

Text #5

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5171. Min Act: -0.1700

Data Index: 8631220 (Open Web Text)

Max Activating Token Index: 695

Text #6

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5171. Min Act: -0.1700

Data Index: 6884183 (Open Web Text)

Max Activating Token Index: 839

Text #7

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.5171. Min Act: -0.1700

Data Index: 1833716 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4859. Min Act: -0.1700

Data Index: 2193759 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4546. Min Act: -0.1700

Data Index: 244961 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4546. Min Act: -0.1700

Data Index: 6032295 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4234. Min Act: -0.1700

Data Index: 4432510 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4234. Min Act: -0.1700

Data Index: 5531682 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.4234. Min Act: -0.1700

Data Index: 7843781 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3921. Min Act: -0.1700

Data Index: 7459702 (Open Web Text)

Max Activating Token Index: 732

Text #15

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3921. Min Act: -0.1700

Data Index: 2594178 (Open Web Text)

Max Activating Token Index: 696

Text #16

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3609. Min Act: -0.1700

Data Index: 453226 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3609. Min Act: -0.1700

Data Index: 1070850 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3609. Min Act: -0.1700

Data Index: 8614800 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.3609. Min Act: -0.1700

Data Index: 2782903 (Open Web Text)

Max Activating Token Index: 607