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

Dataset: Open Web Text

Neuron 2535 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: 3.1522. Min Range: -3.1522

Max Act: 3.1522. Min Act: -0.1700

Data Index: 4617111 (Open Web Text)

Max Activating Token Index: 724

Text #1

Max Range: 3.1522. Min Range: -3.1522

Max Act: 3.0780. Min Act: -0.1700

Data Index: 4105526 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 3.1522. Min Range: -3.1522

Max Act: 3.0666. Min Act: -0.1700

Data Index: 5055851 (Open Web Text)

Max Activating Token Index: 657

Text #3

Max Range: 3.1522. Min Range: -3.1522

Max Act: 3.0383. Min Act: -0.1700

Data Index: 6166548 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 3.1522. Min Range: -3.1522

Max Act: 3.0184. Min Act: -0.1700

Data Index: 717240 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 3.1522. Min Range: -3.1522

Max Act: 3.0261. Min Act: -0.1700

Data Index: 2354178 (Open Web Text)

Max Activating Token Index: 514

Text #6

Max Range: 3.1522. Min Range: -3.1522

Max Act: 3.0256. Min Act: -0.1700

Data Index: 8189311 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9647. Min Act: -0.1700

Data Index: 1710819 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9620. Min Act: -0.1700

Data Index: 3557095 (Open Web Text)

Max Activating Token Index: 744

Text #9

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9831. Min Act: -0.1700

Data Index: 6765441 (Open Web Text)

Max Activating Token Index: 279

Text #10

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9589. Min Act: -0.1700

Data Index: 8460120 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9875. Min Act: -0.1700

Data Index: 612388 (Open Web Text)

Max Activating Token Index: 748

Text #12

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9682. Min Act: -0.1700

Data Index: 3651504 (Open Web Text)

Max Activating Token Index: 79

Text #13

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9219. Min Act: -0.1700

Data Index: 3015666 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9705. Min Act: -0.1700

Data Index: 8476889 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9609. Min Act: -0.1700

Data Index: 5256429 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9597. Min Act: -0.1700

Data Index: 4418904 (Open Web Text)

Max Activating Token Index: 334

Text #17

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9695. Min Act: -0.1700

Data Index: 4376441 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.9439. Min Act: -0.1700

Data Index: 1345607 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 3.1522. Min Range: -3.1522

Max Act: 2.8961. Min Act: -0.1700

Data Index: 7776369 (Open Web Text)

Max Activating Token Index: 779