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

Dataset: Open Web Text

Neuron 1072 in Layer 4

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: 4.0021. Min Range: -4.0021

Max Act: 4.0021. Min Act: -0.1700

Data Index: 6244368 (Open Web Text)

Max Activating Token Index: 764

Text #1

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8539. Min Act: -0.1700

Data Index: 4416922 (Open Web Text)

Max Activating Token Index: 210

Text #2

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8829. Min Act: -0.1700

Data Index: 705483 (Open Web Text)

Max Activating Token Index: 839

Text #3

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8376. Min Act: -0.1700

Data Index: 1088866 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8410. Min Act: -0.1700

Data Index: 2062492 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8341. Min Act: -0.1700

Data Index: 7697348 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8257. Min Act: -0.1700

Data Index: 2011616 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8171. Min Act: -0.1700

Data Index: 1839036 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8385. Min Act: -0.1700

Data Index: 4689448 (Open Web Text)

Max Activating Token Index: 610

Text #9

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7969. Min Act: -0.1700

Data Index: 1739500 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7837. Min Act: -0.1700

Data Index: 3712799 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7872. Min Act: -0.1700

Data Index: 3527980 (Open Web Text)

Max Activating Token Index: 743

Text #12

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8426. Min Act: -0.1700

Data Index: 7950878 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7699. Min Act: -0.1700

Data Index: 7155143 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.8187. Min Act: -0.1700

Data Index: 1088867 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7692. Min Act: -0.1700

Data Index: 3444146 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7437. Min Act: -0.1700

Data Index: 1702947 (Open Web Text)

Max Activating Token Index: 299

Text #17

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7883. Min Act: -0.1700

Data Index: 2633151 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7646. Min Act: -0.1700

Data Index: 271334 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 4.0021. Min Range: -4.0021

Max Act: 3.7767. Min Act: -0.1700

Data Index: 1002263 (Open Web Text)

Max Activating Token Index: 504