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

Dataset: Open Web Text

Neuron 804 in Layer 6

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: 4.1812. Min Range: -4.1812

Max Act: 4.1812. Min Act: -0.1700

Data Index: 4744280 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.9924. Min Act: -0.1700

Data Index: 7053158 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 4.1812. Min Range: -4.1812

Max Act: 4.0276. Min Act: -0.1700

Data Index: 5799313 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.9039. Min Act: -0.1700

Data Index: 1779719 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.9176. Min Act: -0.1700

Data Index: 2189916 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.9996. Min Act: -0.1700

Data Index: 2922685 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.9199. Min Act: -0.1700

Data Index: 7002913 (Open Web Text)

Max Activating Token Index: 686

Text #7

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8617. Min Act: -0.1700

Data Index: 4056046 (Open Web Text)

Max Activating Token Index: 614

Text #8

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8492. Min Act: -0.1700

Data Index: 6183123 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8774. Min Act: -0.1700

Data Index: 3713276 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8704. Min Act: -0.1700

Data Index: 7896461 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8814. Min Act: -0.1700

Data Index: 702206 (Open Web Text)

Max Activating Token Index: 622

Text #12

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8417. Min Act: -0.1700

Data Index: 244412 (Open Web Text)

Max Activating Token Index: 706

Text #13

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8209. Min Act: -0.1700

Data Index: 7257056 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8748. Min Act: -0.1700

Data Index: 5675970 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8777. Min Act: -0.1700

Data Index: 740049 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.8029. Min Act: -0.1700

Data Index: 3541516 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.7987. Min Act: -0.1700

Data Index: 6649084 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.7588. Min Act: -0.1700

Data Index: 6296282 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 4.1812. Min Range: -4.1812

Max Act: 3.7579. Min Act: -0.1700

Data Index: 5772432 (Open Web Text)

Max Activating Token Index: 465