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

Dataset: Open Web Text

Neuron 326 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: 2.8984. Min Range: -2.8984

Max Act: 2.8984. Min Act: -0.1700

Data Index: 2397776 (Open Web Text)

Max Activating Token Index: 612

Text #1

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8828. Min Act: -0.1700

Data Index: 3867894 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8359. Min Act: -0.1700

Data Index: 5543868 (Open Web Text)

Max Activating Token Index: 716

Text #3

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8257. Min Act: -0.1700

Data Index: 5128013 (Open Web Text)

Max Activating Token Index: 664

Text #4

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8440. Min Act: -0.1700

Data Index: 404473 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8288. Min Act: -0.1700

Data Index: 3013571 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8181. Min Act: -0.1700

Data Index: 4631953 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8118. Min Act: -0.1700

Data Index: 6946484 (Open Web Text)

Max Activating Token Index: 297

Text #8

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8063. Min Act: -0.1700

Data Index: 6343279 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8059. Min Act: -0.1700

Data Index: 7079900 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8082. Min Act: -0.1700

Data Index: 2637093 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8044. Min Act: -0.1700

Data Index: 2569815 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7985. Min Act: -0.1700

Data Index: 695441 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.8012. Min Act: -0.1700

Data Index: 8270908 (Open Web Text)

Max Activating Token Index: 614

Text #14

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7913. Min Act: -0.1700

Data Index: 2286538 (Open Web Text)

Max Activating Token Index: 789

Text #15

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7838. Min Act: -0.1700

Data Index: 2835552 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7828. Min Act: -0.1700

Data Index: 4190715 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7812. Min Act: -0.1700

Data Index: 6375896 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7852. Min Act: -0.1700

Data Index: 1707558 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 2.8984. Min Range: -2.8984

Max Act: 2.7882. Min Act: -0.1700

Data Index: 7282380 (Open Web Text)

Max Activating Token Index: 2