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

Dataset: Open Web Text

Neuron 479 in Layer 0

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: 3.7205. Min Range: -3.7205

Max Act: 3.7205. Min Act: -0.1700

Data Index: 6847646 (Open Web Text)

Max Activating Token Index: 900

Text #1

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.7158. Min Act: -0.1700

Data Index: 937068 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6826. Min Act: -0.1700

Data Index: 1560823 (Open Web Text)

Max Activating Token Index: 844

Text #3

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6826. Min Act: -0.1700

Data Index: 2050391 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6815. Min Act: -0.1700

Data Index: 1503544 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6908. Min Act: -0.1700

Data Index: 3436263 (Open Web Text)

Max Activating Token Index: 918

Text #6

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6931. Min Act: -0.1700

Data Index: 5940949 (Open Web Text)

Max Activating Token Index: 655

Text #7

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.7003. Min Act: -0.1700

Data Index: 5588918 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6865. Min Act: -0.1700

Data Index: 7614591 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6862. Min Act: -0.1700

Data Index: 7539379 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6628. Min Act: -0.1700

Data Index: 7252479 (Open Web Text)

Max Activating Token Index: 830

Text #11

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6335. Min Act: -0.1700

Data Index: 5315853 (Open Web Text)

Max Activating Token Index: 938

Text #12

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6473. Min Act: -0.1700

Data Index: 5853844 (Open Web Text)

Max Activating Token Index: 423

Text #13

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6611. Min Act: -0.1700

Data Index: 147980 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6471. Min Act: -0.1700

Data Index: 2490883 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6735. Min Act: -0.1700

Data Index: 6375746 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6546. Min Act: -0.1700

Data Index: 1425382 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6583. Min Act: -0.1700

Data Index: 841481 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6517. Min Act: -0.1700

Data Index: 1461721 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 3.7205. Min Range: -3.7205

Max Act: 3.6571. Min Act: -0.1700

Data Index: 3516348 (Open Web Text)

Max Activating Token Index: 798