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

Dataset: Open Web Text

Neuron 137 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: 6.1653. Min Range: -6.1653

Max Act: 6.1653. Min Act: -0.1699

Data Index: 1856006 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 6.1653. Min Range: -6.1653

Max Act: 6.0649. Min Act: -0.1700

Data Index: 715842 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 6.1653. Min Range: -6.1653

Max Act: 6.0422. Min Act: -0.1700

Data Index: 8336747 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 6.1653. Min Range: -6.1653

Max Act: 6.0350. Min Act: -0.1697

Data Index: 2622595 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.1653. Min Range: -6.1653

Max Act: 6.0031. Min Act: -0.1700

Data Index: 6537001 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9998. Min Act: -0.1700

Data Index: 1688666 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9961. Min Act: -0.1700

Data Index: 834371 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9630. Min Act: -0.1700

Data Index: 166003 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9855. Min Act: -0.1700

Data Index: 2168900 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9868. Min Act: -0.1667

Data Index: 2353462 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9277. Min Act: -0.1700

Data Index: 354083 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9277. Min Act: -0.1700

Data Index: 1103009 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9277. Min Act: -0.1700

Data Index: 2528915 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9571. Min Act: -0.1695

Data Index: 38180 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9277. Min Act: -0.1700

Data Index: 2401170 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9517. Min Act: -0.1696

Data Index: 2307012 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9438. Min Act: -0.1700

Data Index: 643180 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9274. Min Act: -0.1700

Data Index: 614824 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9277. Min Act: -0.1700

Data Index: 504393 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 6.1653. Min Range: -6.1653

Max Act: 5.9277. Min Act: -0.1700

Data Index: 1846932 (Open Web Text)

Max Activating Token Index: 6