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

Dataset: Open Web Text

Neuron 867 in Layer 3

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: 3.7608. Min Range: -3.7608

Max Act: 3.7608. Min Act: -0.1700

Data Index: 7110319 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.7406. Min Act: -0.1700

Data Index: 8572514 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.7247. Min Act: -0.1700

Data Index: 7610911 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.7470. Min Act: -0.1700

Data Index: 3102770 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6310. Min Act: -0.1700

Data Index: 3910877 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6630. Min Act: -0.1700

Data Index: 637083 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6733. Min Act: -0.1700

Data Index: 8169770 (Open Web Text)

Max Activating Token Index: 903

Text #7

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6567. Min Act: -0.1700

Data Index: 7328247 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5812. Min Act: -0.1700

Data Index: 1094700 (Open Web Text)

Max Activating Token Index: 755

Text #9

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6270. Min Act: -0.1700

Data Index: 576950 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5834. Min Act: -0.1700

Data Index: 645833 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6141. Min Act: -0.1700

Data Index: 3104858 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6053. Min Act: -0.1700

Data Index: 17660 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5678. Min Act: -0.1700

Data Index: 1001898 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6063. Min Act: -0.1700

Data Index: 1017958 (Open Web Text)

Max Activating Token Index: 548

Text #15

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.6019. Min Act: -0.1700

Data Index: 7019972 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5960. Min Act: -0.1700

Data Index: 4563798 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5624. Min Act: -0.1700

Data Index: 2199530 (Open Web Text)

Max Activating Token Index: 740

Text #18

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5810. Min Act: -0.1700

Data Index: 5387501 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 3.7608. Min Range: -3.7608

Max Act: 3.5611. Min Act: -0.1700

Data Index: 1830529 (Open Web Text)

Max Activating Token Index: 111