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

Dataset: Open Web Text

Neuron 2595 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: 4.8420. Min Range: -4.8420

Max Act: 4.7693. Min Act: -0.1700

Data Index: 2051822 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7960. Min Act: -0.1700

Data Index: 8263350 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7543. Min Act: -0.1700

Data Index: 3951961 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.8420. Min Act: -0.1700

Data Index: 5911330 (Open Web Text)

Max Activating Token Index: 771

Text #4

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.8023. Min Act: -0.1700

Data Index: 3270324 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6672. Min Act: -0.1700

Data Index: 2388220 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7757. Min Act: -0.1700

Data Index: 7754227 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7342. Min Act: -0.1700

Data Index: 3476268 (Open Web Text)

Max Activating Token Index: 930

Text #8

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7322. Min Act: -0.1700

Data Index: 7602904 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7855. Min Act: -0.1700

Data Index: 6194497 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6916. Min Act: -0.1700

Data Index: 8058069 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6836. Min Act: -0.1700

Data Index: 2708554 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6617. Min Act: -0.1700

Data Index: 651624 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6548. Min Act: -0.1700

Data Index: 8196722 (Open Web Text)

Max Activating Token Index: 237

Text #14

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6508. Min Act: -0.1700

Data Index: 5759167 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6164. Min Act: -0.1700

Data Index: 8771536 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.7011. Min Act: -0.1700

Data Index: 4808866 (Open Web Text)

Max Activating Token Index: 547

Text #17

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6532. Min Act: -0.1700

Data Index: 4857039 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6627. Min Act: -0.1700

Data Index: 5980454 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 4.8420. Min Range: -4.8420

Max Act: 4.6145. Min Act: -0.1700

Data Index: 3654696 (Open Web Text)

Max Activating Token Index: 691