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

Dataset: Open Web Text

Neuron 1464 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: 1.5664. Min Range: -1.5664

Max Act: 1.5664. Min Act: -0.1700

Data Index: 6464069 (Open Web Text)

Max Activating Token Index: 628

Text #1

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5421. Min Act: -0.1700

Data Index: 7607445 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5304. Min Act: -0.1697

Data Index: 7672087 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5310. Min Act: -0.1686

Data Index: 7532943 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5202. Min Act: -0.1700

Data Index: 8202563 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5183. Min Act: -0.1700

Data Index: 4623188 (Open Web Text)

Max Activating Token Index: 522

Text #6

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5081. Min Act: -0.1695

Data Index: 8083867 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5197. Min Act: -0.1700

Data Index: 3067944 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5074. Min Act: -0.1700

Data Index: 2874548 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4962. Min Act: -0.1700

Data Index: 5478482 (Open Web Text)

Max Activating Token Index: 568

Text #10

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5021. Min Act: -0.1700

Data Index: 4623189 (Open Web Text)

Max Activating Token Index: 405

Text #11

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4989. Min Act: -0.1700

Data Index: 2646959 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5012. Min Act: -0.1580

Data Index: 1235522 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4965. Min Act: -0.1696

Data Index: 2066555 (Open Web Text)

Max Activating Token Index: 434

Text #14

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4826. Min Act: -0.1700

Data Index: 5124771 (Open Web Text)

Max Activating Token Index: 913

Text #15

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4914. Min Act: -0.1693

Data Index: 1089157 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4824. Min Act: -0.1700

Data Index: 1771849 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4914. Min Act: -0.1700

Data Index: 2668701 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4901. Min Act: -0.1699

Data Index: 3962172 (Open Web Text)

Max Activating Token Index: 283

Text #19

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4879. Min Act: -0.1699

Data Index: 1488004 (Open Web Text)

Max Activating Token Index: 636