Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1963 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7294. Min Act: -0.1700

Data Index: 753609 (Open Web Text)

Max Activating Token Index: 999

Text #1

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6370. Min Act: -0.1700

Data Index: 1169016 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6400. Min Act: -0.1700

Data Index: 6814147 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6346. Min Act: -0.1700

Data Index: 6753003 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6356. Min Act: -0.1700

Data Index: 6411183 (Open Web Text)

Max Activating Token Index: 248

Text #5

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6281. Min Act: -0.1700

Data Index: 7104218 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6268. Min Act: -0.1700

Data Index: 2718953 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6048. Min Act: -0.1700

Data Index: 5466496 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5873. Min Act: -0.1700

Data Index: 6218009 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5860. Min Act: -0.1699

Data Index: 5835277 (Open Web Text)

Max Activating Token Index: 720

Text #10

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5776. Min Act: -0.1700

Data Index: 4718449 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5707. Min Act: -0.1700

Data Index: 704881 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5765. Min Act: -0.1700

Data Index: 6833999 (Open Web Text)

Max Activating Token Index: 287

Text #13

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5666. Min Act: -0.1700

Data Index: 4782654 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5613. Min Act: -0.1700

Data Index: 2284834 (Open Web Text)

Max Activating Token Index: 536

Text #15

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5724. Min Act: -0.1700

Data Index: 4147547 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5679. Min Act: -0.1700

Data Index: 1740510 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5758. Min Act: -0.1699

Data Index: 180011 (Open Web Text)

Max Activating Token Index: 161

Text #18

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5573. Min Act: -0.1700

Data Index: 6137935 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.5564. Min Act: -0.1700

Data Index: 4821721 (Open Web Text)

Max Activating Token Index: 135