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

Dataset: Open Web Text

Neuron 1988 in Layer 5

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: 4.8724. Min Range: -4.8724

Max Act: 4.8724. Min Act: -0.1700

Data Index: 5919843 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.8383. Min Act: -0.1700

Data Index: 8373847 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.8306. Min Act: -0.1700

Data Index: 3365330 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.8311. Min Act: -0.1700

Data Index: 5302139 (Open Web Text)

Max Activating Token Index: 392

Text #4

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7782. Min Act: -0.1700

Data Index: 2810495 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7603. Min Act: -0.1700

Data Index: 3279648 (Open Web Text)

Max Activating Token Index: 925

Text #6

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7025. Min Act: -0.1700

Data Index: 3778598 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7485. Min Act: -0.1700

Data Index: 5280144 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7619. Min Act: -0.1700

Data Index: 7849402 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7202. Min Act: -0.1700

Data Index: 5817596 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7308. Min Act: -0.1700

Data Index: 109278 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7321. Min Act: -0.1700

Data Index: 4269128 (Open Web Text)

Max Activating Token Index: 804

Text #12

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7330. Min Act: -0.1700

Data Index: 5474120 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7303. Min Act: -0.1700

Data Index: 3094733 (Open Web Text)

Max Activating Token Index: 892

Text #14

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7113. Min Act: -0.1700

Data Index: 7752347 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.6927. Min Act: -0.1700

Data Index: 5919853 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7135. Min Act: -0.1700

Data Index: 8309201 (Open Web Text)

Max Activating Token Index: 835

Text #17

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7482. Min Act: -0.1700

Data Index: 3025196 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7147. Min Act: -0.1700

Data Index: 5919857 (Open Web Text)

Max Activating Token Index: 549

Text #19

Max Range: 4.8724. Min Range: -4.8724

Max Act: 4.7375. Min Act: -0.1700

Data Index: 637708 (Open Web Text)

Max Activating Token Index: 481