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

Dataset: Open Web Text

Neuron 1038 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: 3.1812. Min Range: -3.1812

Max Act: 3.1812. Min Act: -0.1700

Data Index: 68261 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1452. Min Act: -0.1700

Data Index: 5009559 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1390. Min Act: -0.1700

Data Index: 2425327 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1271. Min Act: -0.1700

Data Index: 808170 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1023. Min Act: -0.1700

Data Index: 2831561 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1030. Min Act: -0.1700

Data Index: 8414316 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0993. Min Act: -0.1700

Data Index: 5607947 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0962. Min Act: -0.1700

Data Index: 873406 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.1039. Min Act: -0.1700

Data Index: 238959 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1434984 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0831. Min Act: -0.1700

Data Index: 6894949 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0861. Min Act: -0.1700

Data Index: 326664 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0811. Min Act: -0.1700

Data Index: 4602516 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0811. Min Act: -0.1700

Data Index: 6401801 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0798. Min Act: -0.1700

Data Index: 6359318 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0831. Min Act: -0.1700

Data Index: 3643108 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0789. Min Act: -0.1700

Data Index: 5569694 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0831. Min Act: -0.1700

Data Index: 3072183 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0652. Min Act: -0.1700

Data Index: 4448660 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.1812. Min Range: -3.1812

Max Act: 3.0700. Min Act: -0.1700

Data Index: 1218106 (Open Web Text)

Max Activating Token Index: 5