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

Dataset: Open Web Text

Neuron 2958 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: 0.8917. Min Range: -0.8917

Max Act: 0.8917. Min Act: -0.1380

Data Index: 2282338 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8321. Min Act: -0.1526

Data Index: 8166202 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8200. Min Act: -0.1420

Data Index: 6841820 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8145. Min Act: -0.1440

Data Index: 6196475 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8060. Min Act: -0.1537

Data Index: 4120917 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8076. Min Act: -0.1563

Data Index: 8461354 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7951. Min Act: -0.1436

Data Index: 962889 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7989. Min Act: -0.1574

Data Index: 1970159 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8074. Min Act: -0.1648

Data Index: 8278335 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8007. Min Act: -0.1681

Data Index: 1215733 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7893. Min Act: -0.1441

Data Index: 5285977 (Open Web Text)

Max Activating Token Index: 708

Text #11

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7875. Min Act: -0.1251

Data Index: 7560814 (Open Web Text)

Max Activating Token Index: 691

Text #12

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7831. Min Act: -0.1438

Data Index: 4562607 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7888. Min Act: -0.1310

Data Index: 1045995 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7802. Min Act: -0.1644

Data Index: 8685302 (Open Web Text)

Max Activating Token Index: 841

Text #15

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7914. Min Act: -0.1503

Data Index: 7784577 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7901. Min Act: -0.1438

Data Index: 5062724 (Open Web Text)

Max Activating Token Index: 835

Text #17

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7765. Min Act: -0.1676

Data Index: 7365752 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7796. Min Act: -0.1645

Data Index: 4508233 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7795. Min Act: -0.1508

Data Index: 8424886 (Open Web Text)

Max Activating Token Index: 684