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

Dataset: Open Web Text

Neuron 63 in Layer 2

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: 3.0563. Min Range: -3.0563

Max Act: 3.0563. Min Act: -0.1700

Data Index: 5277203 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0191. Min Act: -0.1700

Data Index: 6166444 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9997. Min Act: -0.1700

Data Index: 3467521 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9952. Min Act: -0.1700

Data Index: 8395785 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9763. Min Act: -0.1700

Data Index: 690037 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9907. Min Act: -0.1700

Data Index: 1109724 (Open Web Text)

Max Activating Token Index: 149

Text #6

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9674. Min Act: -0.1700

Data Index: 7931846 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9791. Min Act: -0.1700

Data Index: 65134 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9804. Min Act: -0.1700

Data Index: 218795 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9760. Min Act: -0.1700

Data Index: 8053704 (Open Web Text)

Max Activating Token Index: 177

Text #10

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9472. Min Act: -0.1700

Data Index: 2930278 (Open Web Text)

Max Activating Token Index: 623

Text #11

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9548. Min Act: -0.1700

Data Index: 5964736 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9655. Min Act: -0.1700

Data Index: 1623475 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9538. Min Act: -0.1700

Data Index: 8369851 (Open Web Text)

Max Activating Token Index: 248

Text #14

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9527. Min Act: -0.1700

Data Index: 3172768 (Open Web Text)

Max Activating Token Index: 155

Text #15

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9654. Min Act: -0.1700

Data Index: 7377720 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9508. Min Act: -0.1700

Data Index: 4692554 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9459. Min Act: -0.1700

Data Index: 1262581 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9668. Min Act: -0.1700

Data Index: 7668060 (Open Web Text)

Max Activating Token Index: 874

Text #19

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9629. Min Act: -0.1700

Data Index: 3200150 (Open Web Text)

Max Activating Token Index: 730