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

Dataset: Open Web Text

Neuron 2071 in Layer 3

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: 3.7924. Min Range: -3.7924

Max Act: 3.7924. Min Act: -0.1700

Data Index: 1470926 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.7662. Min Act: -0.1700

Data Index: 926374 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.7296. Min Act: -0.1700

Data Index: 844903 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6865. Min Act: -0.1700

Data Index: 1963879 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6616. Min Act: -0.1700

Data Index: 1676619 (Open Web Text)

Max Activating Token Index: 939

Text #5

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6846. Min Act: -0.1700

Data Index: 3149942 (Open Web Text)

Max Activating Token Index: 705

Text #6

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6550. Min Act: -0.1700

Data Index: 2944944 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6686. Min Act: -0.1700

Data Index: 1849234 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6646. Min Act: -0.1700

Data Index: 3983213 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6149. Min Act: -0.1700

Data Index: 2512348 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6414. Min Act: -0.1700

Data Index: 8068824 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6465. Min Act: -0.1700

Data Index: 1842163 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6081. Min Act: -0.1700

Data Index: 1102156 (Open Web Text)

Max Activating Token Index: 152

Text #13

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6329. Min Act: -0.1700

Data Index: 5267865 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5969. Min Act: -0.1700

Data Index: 6385459 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6400. Min Act: -0.1700

Data Index: 1856178 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6073. Min Act: -0.1700

Data Index: 4475817 (Open Web Text)

Max Activating Token Index: 152

Text #17

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6188. Min Act: -0.1700

Data Index: 2564408 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5730. Min Act: -0.1700

Data Index: 1593267 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5828. Min Act: -0.1700

Data Index: 6368966 (Open Web Text)

Max Activating Token Index: 247