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

Dataset: Open Web Text

Neuron 1695 in Layer 0

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: 5.1836. Min Range: -5.1836

Max Act: 5.1836. Min Act: -0.1700

Data Index: 3307142 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1348. Min Act: -0.1700

Data Index: 3515448 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1361. Min Act: -0.1700

Data Index: 725616 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1128. Min Act: -0.1700

Data Index: 4563610 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1049. Min Act: -0.1700

Data Index: 3507326 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0878. Min Act: -0.1700

Data Index: 1609343 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0858. Min Act: -0.1700

Data Index: 770039 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1074. Min Act: -0.1700

Data Index: 6531614 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1184. Min Act: -0.1700

Data Index: 6168593 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.1096. Min Act: -0.1700

Data Index: 419658 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0667. Min Act: -0.1700

Data Index: 1607633 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0872. Min Act: -0.1700

Data Index: 5765006 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0810. Min Act: -0.1700

Data Index: 3679445 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0646. Min Act: -0.1700

Data Index: 867812 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0644. Min Act: -0.1700

Data Index: 3208985 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0211. Min Act: -0.1700

Data Index: 3494147 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0317. Min Act: -0.1700

Data Index: 2622002 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0291. Min Act: -0.1699

Data Index: 4226197 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0444. Min Act: -0.1700

Data Index: 3038378 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.1836. Min Range: -5.1836

Max Act: 5.0457. Min Act: -0.1700

Data Index: 4335542 (Open Web Text)

Max Activating Token Index: 4