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

Dataset: Open Web Text

Neuron 813 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: 1.9819. Min Range: -1.9819

Max Act: 1.9815. Min Act: -0.1598

Data Index: 5099137 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9756. Min Act: -0.1700

Data Index: 3084352 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9760. Min Act: -0.1699

Data Index: 3685640 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9819. Min Act: -0.1700

Data Index: 1806730 (Open Web Text)

Max Activating Token Index: 118

Text #4

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9698. Min Act: -0.1691

Data Index: 2179753 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9694. Min Act: -0.1700

Data Index: 6034996 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9662. Min Act: -0.1700

Data Index: 5377808 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9667. Min Act: -0.1646

Data Index: 93810 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9631. Min Act: -0.1700

Data Index: 243665 (Open Web Text)

Max Activating Token Index: 530

Text #9

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9567. Min Act: -0.1698

Data Index: 5349884 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9618. Min Act: -0.1654

Data Index: 9490 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9504. Min Act: -0.1700

Data Index: 3960273 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9578. Min Act: -0.1699

Data Index: 4812391 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9666. Min Act: -0.1700

Data Index: 6663758 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9498. Min Act: -0.1699

Data Index: 7036602 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9592. Min Act: -0.1700

Data Index: 8490295 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9462. Min Act: -0.1700

Data Index: 6525391 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9523. Min Act: -0.1700

Data Index: 2195997 (Open Web Text)

Max Activating Token Index: 1006

Text #18

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9507. Min Act: -0.1699

Data Index: 4265683 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 1.9819. Min Range: -1.9819

Max Act: 1.9531. Min Act: -0.1700

Data Index: 949480 (Open Web Text)

Max Activating Token Index: 545