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

Dataset: Open Web Text

Neuron 1966 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: 4.1741. Min Range: -4.1741

Max Act: 4.1691. Min Act: -0.1700

Data Index: 4095280 (Open Web Text)

Max Activating Token Index: 146

Text #1

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1072. Min Act: -0.1700

Data Index: 728859 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1210. Min Act: -0.1700

Data Index: 1336318 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0616. Min Act: -0.1700

Data Index: 5740729 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1741. Min Act: -0.1700

Data Index: 6335507 (Open Web Text)

Max Activating Token Index: 575

Text #5

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1098. Min Act: -0.1700

Data Index: 4072859 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0808. Min Act: -0.1700

Data Index: 2647334 (Open Web Text)

Max Activating Token Index: 770

Text #7

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0573. Min Act: -0.1700

Data Index: 1890093 (Open Web Text)

Max Activating Token Index: 453

Text #8

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0690. Min Act: -0.1700

Data Index: 7886026 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0218. Min Act: -0.1700

Data Index: 1770027 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9945. Min Act: -0.1700

Data Index: 4473218 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0657. Min Act: -0.1700

Data Index: 4362889 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9546. Min Act: -0.1700

Data Index: 869291 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9267. Min Act: -0.1700

Data Index: 1794531 (Open Web Text)

Max Activating Token Index: 749

Text #14

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9957. Min Act: -0.1700

Data Index: 4059757 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9652. Min Act: -0.1700

Data Index: 3106628 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0487. Min Act: -0.1700

Data Index: 365372 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9065. Min Act: -0.1700

Data Index: 935869 (Open Web Text)

Max Activating Token Index: 894

Text #18

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9895. Min Act: -0.1700

Data Index: 1398827 (Open Web Text)

Max Activating Token Index: 712

Text #19

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9470. Min Act: -0.1700

Data Index: 4479034 (Open Web Text)

Max Activating Token Index: 583