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

Dataset: Open Web Text

Neuron 373 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: 4.1318. Min Range: -4.1318

Max Act: 4.1318. Min Act: -0.1700

Data Index: 1400882 (Open Web Text)

Max Activating Token Index: 810

Text #1

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0613. Min Act: -0.1700

Data Index: 2504882 (Open Web Text)

Max Activating Token Index: 934

Text #2

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0563. Min Act: -0.1700

Data Index: 6222127 (Open Web Text)

Max Activating Token Index: 722

Text #3

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0433. Min Act: -0.1700

Data Index: 3848550 (Open Web Text)

Max Activating Token Index: 599

Text #4

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0343. Min Act: -0.1700

Data Index: 8641474 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0185. Min Act: -0.1700

Data Index: 2065122 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0031. Min Act: -0.1700

Data Index: 3811507 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9859. Min Act: -0.1700

Data Index: 8482817 (Open Web Text)

Max Activating Token Index: 443

Text #8

Max Range: 4.1318. Min Range: -4.1318

Max Act: 4.0091. Min Act: -0.1700

Data Index: 5079644 (Open Web Text)

Max Activating Token Index: 704

Text #9

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9495. Min Act: -0.1700

Data Index: 1418628 (Open Web Text)

Max Activating Token Index: 920

Text #10

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9604. Min Act: -0.1700

Data Index: 5661730 (Open Web Text)

Max Activating Token Index: 130

Text #11

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9682. Min Act: -0.1700

Data Index: 8819289 (Open Web Text)

Max Activating Token Index: 261

Text #12

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9748. Min Act: -0.1700

Data Index: 1878007 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9756. Min Act: -0.1700

Data Index: 2552631 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9620. Min Act: -0.1700

Data Index: 8317797 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9667. Min Act: -0.1700

Data Index: 6571497 (Open Web Text)

Max Activating Token Index: 903

Text #16

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9500. Min Act: -0.1700

Data Index: 4692422 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9756. Min Act: -0.1700

Data Index: 6049254 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9326. Min Act: -0.1700

Data Index: 2005821 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 4.1318. Min Range: -4.1318

Max Act: 3.9436. Min Act: -0.1700

Data Index: 5944715 (Open Web Text)

Max Activating Token Index: 550