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

Dataset: Open Web Text

Neuron 2874 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: 3.7518. Min Range: -3.7518

Max Act: 3.7518. Min Act: -0.1700

Data Index: 3215820 (Open Web Text)

Max Activating Token Index: 902

Text #1

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.6343. Min Act: -0.1700

Data Index: 3332164 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.5490. Min Act: -0.1700

Data Index: 6514009 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.4438. Min Act: -0.1700

Data Index: 8581527 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.4359. Min Act: -0.1700

Data Index: 3255231 (Open Web Text)

Max Activating Token Index: 786

Text #5

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.4267. Min Act: -0.1700

Data Index: 8145580 (Open Web Text)

Max Activating Token Index: 101

Text #6

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.4121. Min Act: -0.1700

Data Index: 5377399 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3894. Min Act: -0.1700

Data Index: 2424193 (Open Web Text)

Max Activating Token Index: 596

Text #8

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3827. Min Act: -0.1700

Data Index: 5120016 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3609. Min Act: -0.1700

Data Index: 3217353 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3576. Min Act: -0.1700

Data Index: 8168310 (Open Web Text)

Max Activating Token Index: 997

Text #11

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3098. Min Act: -0.1700

Data Index: 8167138 (Open Web Text)

Max Activating Token Index: 759

Text #12

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3209. Min Act: -0.1700

Data Index: 3384065 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3055. Min Act: -0.1700

Data Index: 3752468 (Open Web Text)

Max Activating Token Index: 790

Text #14

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.2892. Min Act: -0.1700

Data Index: 4868428 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.2671. Min Act: -0.1700

Data Index: 1275321 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.2849. Min Act: -0.1700

Data Index: 534815 (Open Web Text)

Max Activating Token Index: 701

Text #17

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.3023. Min Act: -0.1700

Data Index: 5137376 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.2975. Min Act: -0.1700

Data Index: 132945 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 3.7518. Min Range: -3.7518

Max Act: 3.2738. Min Act: -0.1700

Data Index: 7302794 (Open Web Text)

Max Activating Token Index: 1009