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

Dataset: Open Web Text

Neuron 1392 in Layer 1

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: 3.9914. Min Range: -3.9914

Max Act: 3.9914. Min Act: -0.1700

Data Index: 3203522 (Open Web Text)

Max Activating Token Index: 126

Text #1

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.9212. Min Act: -0.1700

Data Index: 5304687 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.9218. Min Act: -0.1700

Data Index: 3203523 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.8386. Min Act: -0.1700

Data Index: 7917489 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.8589. Min Act: -0.1700

Data Index: 6317093 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.8069. Min Act: -0.1700

Data Index: 3099042 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.7974. Min Act: -0.1700

Data Index: 5340727 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.8184. Min Act: -0.1700

Data Index: 6317087 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.7665. Min Act: -0.1700

Data Index: 286221 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.7325. Min Act: -0.1700

Data Index: 1476360 (Open Web Text)

Max Activating Token Index: 251

Text #10

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.7406. Min Act: -0.1700

Data Index: 2723 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6996. Min Act: -0.1700

Data Index: 7572349 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6946. Min Act: -0.1700

Data Index: 2717 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.7126. Min Act: -0.1700

Data Index: 1316092 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.7354. Min Act: -0.1700

Data Index: 2714 (Open Web Text)

Max Activating Token Index: 655

Text #15

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1840301 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6668. Min Act: -0.1700

Data Index: 1840303 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6733. Min Act: -0.1700

Data Index: 1316097 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6588. Min Act: -0.1700

Data Index: 1406732 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 3.9914. Min Range: -3.9914

Max Act: 3.6550. Min Act: -0.1700

Data Index: 1840300 (Open Web Text)

Max Activating Token Index: 668