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

Dataset: Open Web Text

Neuron 1357 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: 3.1008. Min Range: -3.1008

Max Act: 3.1008. Min Act: -0.1700

Data Index: 3004174 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.1008. Min Range: -3.1008

Max Act: 3.0366. Min Act: -0.1700

Data Index: 6243614 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9979. Min Act: -0.1700

Data Index: 8406060 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9817. Min Act: -0.1700

Data Index: 1418468 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9871. Min Act: -0.1700

Data Index: 7853952 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9610. Min Act: -0.1700

Data Index: 4680979 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9594. Min Act: -0.1700

Data Index: 5444444 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9575. Min Act: -0.1700

Data Index: 3477253 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9641. Min Act: -0.1700

Data Index: 7849074 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9515. Min Act: -0.1700

Data Index: 6312380 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9473. Min Act: -0.1700

Data Index: 4114580 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9195. Min Act: -0.1700

Data Index: 7840607 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9376. Min Act: -0.1700

Data Index: 1175833 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9205. Min Act: -0.1700

Data Index: 4699031 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9449. Min Act: -0.1700

Data Index: 6255835 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9165. Min Act: -0.1700

Data Index: 7093743 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9301. Min Act: -0.1700

Data Index: 3650131 (Open Web Text)

Max Activating Token Index: 169

Text #17

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9366. Min Act: -0.1700

Data Index: 5448795 (Open Web Text)

Max Activating Token Index: 409

Text #18

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.9023. Min Act: -0.1700

Data Index: 4510234 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 3.1008. Min Range: -3.1008

Max Act: 2.8865. Min Act: -0.1700

Data Index: 4525093 (Open Web Text)

Max Activating Token Index: 12