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

Dataset: Open Web Text

Neuron 2195 in Layer 1

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: 3.1836. Min Range: -3.1836

Max Act: 3.1836. Min Act: -0.1700

Data Index: 6028584 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1692. Min Act: -0.1700

Data Index: 7273052 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1249. Min Act: -0.1700

Data Index: 3376323 (Open Web Text)

Max Activating Token Index: 367

Text #3

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1304. Min Act: -0.1700

Data Index: 3936202 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1247. Min Act: -0.1700

Data Index: 4066238 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1167. Min Act: -0.1700

Data Index: 8817118 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1064. Min Act: -0.1700

Data Index: 4542869 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1086. Min Act: -0.1700

Data Index: 7027874 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0973. Min Act: -0.1700

Data Index: 6112160 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1016. Min Act: -0.1700

Data Index: 1494290 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0827. Min Act: -0.1700

Data Index: 1564226 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1004. Min Act: -0.1700

Data Index: 2049602 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.1004. Min Act: -0.1700

Data Index: 8352381 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0722. Min Act: -0.1700

Data Index: 5612479 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0536. Min Act: -0.1700

Data Index: 1658702 (Open Web Text)

Max Activating Token Index: 111

Text #15

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0711. Min Act: -0.1700

Data Index: 3746241 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0861. Min Act: -0.1700

Data Index: 1119889 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0719. Min Act: -0.1700

Data Index: 169294 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0707. Min Act: -0.1700

Data Index: 7487746 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.1836. Min Range: -3.1836

Max Act: 3.0706. Min Act: -0.1700

Data Index: 4030460 (Open Web Text)

Max Activating Token Index: 33