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

Dataset: Open Web Text

Neuron 1321 in Layer 2

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: 3.8835. Min Range: -3.8835

Max Act: 3.8835. Min Act: -0.1700

Data Index: 5614799 (Open Web Text)

Max Activating Token Index: 877

Text #1

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.8512. Min Act: -0.1700

Data Index: 7455274 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7275. Min Act: -0.1700

Data Index: 5743554 (Open Web Text)

Max Activating Token Index: 570

Text #3

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7362. Min Act: -0.1700

Data Index: 789879 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7103. Min Act: -0.1700

Data Index: 7047622 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7162. Min Act: -0.1700

Data Index: 5167479 (Open Web Text)

Max Activating Token Index: 147

Text #6

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.7068. Min Act: -0.1700

Data Index: 196085 (Open Web Text)

Max Activating Token Index: 830

Text #7

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6931. Min Act: -0.1700

Data Index: 3234518 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6864. Min Act: -0.1700

Data Index: 5743559 (Open Web Text)

Max Activating Token Index: 620

Text #9

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6496. Min Act: -0.1700

Data Index: 196082 (Open Web Text)

Max Activating Token Index: 945

Text #10

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6400. Min Act: -0.1700

Data Index: 4110418 (Open Web Text)

Max Activating Token Index: 870

Text #11

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6521. Min Act: -0.1700

Data Index: 7783680 (Open Web Text)

Max Activating Token Index: 437

Text #12

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6463. Min Act: -0.1700

Data Index: 3115668 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6095. Min Act: -0.1700

Data Index: 4720112 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6259. Min Act: -0.1700

Data Index: 8101891 (Open Web Text)

Max Activating Token Index: 631

Text #15

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1953724 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.5843. Min Act: -0.1700

Data Index: 661316 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.5835. Min Act: -0.1700

Data Index: 4955756 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1767716 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 3.8835. Min Range: -3.8835

Max Act: 3.5842. Min Act: -0.1700

Data Index: 3065663 (Open Web Text)

Max Activating Token Index: 722