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

Dataset: Open Web Text

Neuron 872 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: 4.0122. Min Range: -4.0122

Max Act: 4.0122. Min Act: -0.1700

Data Index: 7588886 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.9829. Min Act: -0.1700

Data Index: 7407577 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.9401. Min Act: -0.1700

Data Index: 259653 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.9521. Min Act: -0.1700

Data Index: 2419543 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.9321. Min Act: -0.1700

Data Index: 3014927 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.9195. Min Act: -0.1700

Data Index: 6145660 (Open Web Text)

Max Activating Token Index: 861

Text #6

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8543. Min Act: -0.1700

Data Index: 2900233 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8656. Min Act: -0.1700

Data Index: 3062691 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8686. Min Act: -0.1700

Data Index: 8223539 (Open Web Text)

Max Activating Token Index: 109

Text #9

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8524. Min Act: -0.1700

Data Index: 6141936 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8133. Min Act: -0.1700

Data Index: 4248586 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8400. Min Act: -0.1700

Data Index: 5831781 (Open Web Text)

Max Activating Token Index: 174

Text #12

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8677. Min Act: -0.1700

Data Index: 1779480 (Open Web Text)

Max Activating Token Index: 952

Text #13

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8228. Min Act: -0.1700

Data Index: 6605228 (Open Web Text)

Max Activating Token Index: 858

Text #14

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8433. Min Act: -0.1700

Data Index: 7920598 (Open Web Text)

Max Activating Token Index: 599

Text #15

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8718. Min Act: -0.1700

Data Index: 3905490 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8480. Min Act: -0.1700

Data Index: 5952844 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8458. Min Act: -0.1700

Data Index: 3080439 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8249. Min Act: -0.1700

Data Index: 6529935 (Open Web Text)

Max Activating Token Index: 123

Text #19

Max Range: 4.0122. Min Range: -4.0122

Max Act: 3.8461. Min Act: -0.1700

Data Index: 5242428 (Open Web Text)

Max Activating Token Index: 211