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

Dataset: Open Web Text

Neuron 2466 in Layer 5

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: 4.9544. Min Range: -4.9544

Max Act: 4.9544. Min Act: -0.1700

Data Index: 2152639 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.8472. Min Act: -0.1700

Data Index: 890115 (Open Web Text)

Max Activating Token Index: 577

Text #2

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7512. Min Act: -0.1700

Data Index: 907071 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7523. Min Act: -0.1700

Data Index: 7629121 (Open Web Text)

Max Activating Token Index: 253

Text #4

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7574. Min Act: -0.1700

Data Index: 6887 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7275. Min Act: -0.1700

Data Index: 2845423 (Open Web Text)

Max Activating Token Index: 964

Text #6

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6918. Min Act: -0.1700

Data Index: 1069829 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6962. Min Act: -0.1700

Data Index: 709013 (Open Web Text)

Max Activating Token Index: 605

Text #8

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6840. Min Act: -0.1700

Data Index: 8606249 (Open Web Text)

Max Activating Token Index: 421

Text #9

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6942. Min Act: -0.1700

Data Index: 6790875 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7054. Min Act: -0.1700

Data Index: 969029 (Open Web Text)

Max Activating Token Index: 263

Text #11

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7180. Min Act: -0.1700

Data Index: 787801 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6799. Min Act: -0.1700

Data Index: 6569300 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6766. Min Act: -0.1700

Data Index: 2542917 (Open Web Text)

Max Activating Token Index: 723

Text #14

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6855. Min Act: -0.1700

Data Index: 1624206 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6688. Min Act: -0.1700

Data Index: 6364405 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.7073. Min Act: -0.1700

Data Index: 2312066 (Open Web Text)

Max Activating Token Index: 514

Text #17

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6725. Min Act: -0.1700

Data Index: 6991974 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6631. Min Act: -0.1700

Data Index: 7260168 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 4.9544. Min Range: -4.9544

Max Act: 4.6504. Min Act: -0.1700

Data Index: 3640104 (Open Web Text)

Max Activating Token Index: 3