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

Dataset: Open Web Text

Neuron 1348 in Layer 3

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: 3.7321. Min Range: -3.7321

Max Act: 3.7321. Min Act: -0.1700

Data Index: 7116042 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.6892. Min Act: -0.1700

Data Index: 7577882 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.5678. Min Act: -0.1700

Data Index: 4010866 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.6085. Min Act: -0.1700

Data Index: 6559882 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.5791. Min Act: -0.1700

Data Index: 3130669 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4945. Min Act: -0.1700

Data Index: 860330 (Open Web Text)

Max Activating Token Index: 958

Text #6

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4851. Min Act: -0.1700

Data Index: 6487254 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4878. Min Act: -0.1700

Data Index: 7023156 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4871. Min Act: -0.1700

Data Index: 3507183 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4835. Min Act: -0.1700

Data Index: 2990918 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4877. Min Act: -0.1700

Data Index: 1785439 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4556. Min Act: -0.1700

Data Index: 6217782 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4495. Min Act: -0.1700

Data Index: 8493352 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4687. Min Act: -0.1700

Data Index: 3485845 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4642. Min Act: -0.1700

Data Index: 1352296 (Open Web Text)

Max Activating Token Index: 510

Text #15

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4413. Min Act: -0.1700

Data Index: 5128560 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4679. Min Act: -0.1700

Data Index: 4538102 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4654. Min Act: -0.1700

Data Index: 8138508 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4639. Min Act: -0.1700

Data Index: 66360 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.7321. Min Range: -3.7321

Max Act: 3.4356. Min Act: -0.1700

Data Index: 945514 (Open Web Text)

Max Activating Token Index: 471