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

Dataset: Open Web Text

Neuron 1111 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: 3.3802. Min Range: -3.3802

Max Act: 3.3802. Min Act: -0.1700

Data Index: 698006 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.2910. Min Act: -0.1700

Data Index: 1491278 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.2662. Min Act: -0.1700

Data Index: 2182612 (Open Web Text)

Max Activating Token Index: 836

Text #3

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.2587. Min Act: -0.1700

Data Index: 5701451 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.2879. Min Act: -0.1700

Data Index: 6359519 (Open Web Text)

Max Activating Token Index: 693

Text #5

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1838. Min Act: -0.1700

Data Index: 3323878 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1281. Min Act: -0.1700

Data Index: 2997502 (Open Web Text)

Max Activating Token Index: 648

Text #7

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1542. Min Act: -0.1700

Data Index: 1928135 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1465. Min Act: -0.1700

Data Index: 4039869 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1373. Min Act: -0.1700

Data Index: 7398799 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1174. Min Act: -0.1700

Data Index: 787846 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1033. Min Act: -0.1700

Data Index: 6576701 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1450. Min Act: -0.1700

Data Index: 7498111 (Open Web Text)

Max Activating Token Index: 560

Text #13

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.0705. Min Act: -0.1700

Data Index: 2800577 (Open Web Text)

Max Activating Token Index: 940

Text #14

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.0912. Min Act: -0.1700

Data Index: 2528778 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.1058. Min Act: -0.1700

Data Index: 1113219 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.0949. Min Act: -0.1700

Data Index: 521107 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.0807. Min Act: -0.1700

Data Index: 5938980 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.0663. Min Act: -0.1700

Data Index: 2274067 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 3.3802. Min Range: -3.3802

Max Act: 3.0246. Min Act: -0.1700

Data Index: 117922 (Open Web Text)

Max Activating Token Index: 491