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

Dataset: Open Web Text

Neuron 58 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: 2.5945. Min Range: -2.5945

Max Act: 2.5945. Min Act: -0.1700

Data Index: 5797187 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5727. Min Act: -0.1700

Data Index: 2214163 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5654. Min Act: -0.1700

Data Index: 6580133 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5535. Min Act: -0.1700

Data Index: 3143818 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5707. Min Act: -0.1700

Data Index: 2551 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5526. Min Act: -0.1700

Data Index: 7428891 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5619. Min Act: -0.1700

Data Index: 1277671 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5580. Min Act: -0.1700

Data Index: 2707224 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5275. Min Act: -0.1700

Data Index: 796939 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5365. Min Act: -0.1700

Data Index: 6887877 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5235. Min Act: -0.1700

Data Index: 6818832 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5216. Min Act: -0.1700

Data Index: 6029773 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5027. Min Act: -0.1700

Data Index: 8343334 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5199. Min Act: -0.1700

Data Index: 5424858 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5068. Min Act: -0.1700

Data Index: 934868 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5196. Min Act: -0.1700

Data Index: 6663369 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.5020. Min Act: -0.1700

Data Index: 655017 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.4897. Min Act: -0.1700

Data Index: 4674324 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.4940. Min Act: -0.1700

Data Index: 6042895 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.5945. Min Range: -2.5945

Max Act: 2.4980. Min Act: -0.1700

Data Index: 4871032 (Open Web Text)

Max Activating Token Index: 4