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

Dataset: Open Web Text

Neuron 1621 in Layer 6

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: 3.2544. Min Range: -3.2544

Max Act: 3.2544. Min Act: -0.1700

Data Index: 5877866 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.2321. Min Act: -0.1700

Data Index: 3467391 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.1886. Min Act: -0.1700

Data Index: 7354516 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1035408 (Open Web Text)

Max Activating Token Index: 934

Text #4

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0870. Min Act: -0.1700

Data Index: 6684471 (Open Web Text)

Max Activating Token Index: 459

Text #5

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0856. Min Act: -0.1700

Data Index: 8036028 (Open Web Text)

Max Activating Token Index: 742

Text #6

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0839. Min Act: -0.1700

Data Index: 3160247 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0901. Min Act: -0.1700

Data Index: 8709021 (Open Web Text)

Max Activating Token Index: 733

Text #8

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0640. Min Act: -0.1700

Data Index: 5846739 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0586. Min Act: -0.1700

Data Index: 936 (Open Web Text)

Max Activating Token Index: 667

Text #10

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0300. Min Act: -0.1700

Data Index: 2175544 (Open Web Text)

Max Activating Token Index: 1006

Text #11

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0495. Min Act: -0.1700

Data Index: 7887088 (Open Web Text)

Max Activating Token Index: 904

Text #12

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0406. Min Act: -0.1700

Data Index: 6650132 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0228. Min Act: -0.1700

Data Index: 4153666 (Open Web Text)

Max Activating Token Index: 779

Text #14

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0166. Min Act: -0.1700

Data Index: 7909291 (Open Web Text)

Max Activating Token Index: 692

Text #15

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0004. Min Act: -0.1700

Data Index: 2466426 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0118. Min Act: -0.1700

Data Index: 8202061 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0076. Min Act: -0.1700

Data Index: 5877863 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0096. Min Act: -0.1700

Data Index: 3868685 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 3.2544. Min Range: -3.2544

Max Act: 3.0160. Min Act: -0.1700

Data Index: 3087905 (Open Web Text)

Max Activating Token Index: 592