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

Dataset: Open Web Text

Neuron 709 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: 3.8509. Min Range: -3.8509

Max Act: 3.8509. Min Act: -0.1700

Data Index: 8077209 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.8006. Min Act: -0.1700

Data Index: 3272413 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.8072. Min Act: -0.1700

Data Index: 5485554 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7698. Min Act: -0.1700

Data Index: 2904247 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7825. Min Act: -0.1700

Data Index: 6345973 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7863. Min Act: -0.1700

Data Index: 1724998 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7378. Min Act: -0.1700

Data Index: 6104532 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7299. Min Act: -0.1700

Data Index: 5514641 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7252. Min Act: -0.1700

Data Index: 3324773 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7435. Min Act: -0.1700

Data Index: 1277536 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7402. Min Act: -0.1700

Data Index: 1596166 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7002. Min Act: -0.1700

Data Index: 7184345 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7057. Min Act: -0.1700

Data Index: 3380361 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6910. Min Act: -0.1700

Data Index: 1913078 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1111860 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6714. Min Act: -0.1700

Data Index: 866068 (Open Web Text)

Max Activating Token Index: 865

Text #16

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6614. Min Act: -0.1700

Data Index: 211376 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6760. Min Act: -0.1700

Data Index: 761107 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6895. Min Act: -0.1700

Data Index: 7268267 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6653. Min Act: -0.1700

Data Index: 1875978 (Open Web Text)

Max Activating Token Index: 71