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

Dataset: Open Web Text

Neuron 1133 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: 7.2874. Min Range: -7.2874

Max Act: 7.2281. Min Act: -0.1700

Data Index: 1631888 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2874. Min Act: -0.1699

Data Index: 1745694 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2406. Min Act: -0.1700

Data Index: 1175923 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2684. Min Act: -0.1700

Data Index: 2970288 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2378. Min Act: -0.1700

Data Index: 3728238 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2501. Min Act: -0.1700

Data Index: 5654649 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2155. Min Act: -0.1700

Data Index: 998852 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2351. Min Act: -0.1699

Data Index: 130894 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1876. Min Act: -0.1699

Data Index: 4217262 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1789. Min Act: -0.1688

Data Index: 5031918 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2059. Min Act: -0.1700

Data Index: 1268867 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1688. Min Act: -0.1700

Data Index: 4808678 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1575. Min Act: -0.1700

Data Index: 4476142 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2006. Min Act: -0.1692

Data Index: 4335995 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1820. Min Act: -0.1697

Data Index: 874510 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1729. Min Act: -0.1698

Data Index: 55916 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1596. Min Act: -0.1696

Data Index: 2043809 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1793. Min Act: -0.1700

Data Index: 1975851 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1575. Min Act: -0.1700

Data Index: 564247 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1566. Min Act: -0.1700

Data Index: 255492 (Open Web Text)

Max Activating Token Index: 4