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

Dataset: Open Web Text

Neuron 1686 in Layer 4

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: 3.8065. Min Range: -3.8065

Max Act: 3.8065. Min Act: -0.1700

Data Index: 8147666 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.4688. Min Act: -0.1700

Data Index: 745666 (Open Web Text)

Max Activating Token Index: 945

Text #2

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.4827. Min Act: -0.1700

Data Index: 7816732 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.4534. Min Act: -0.1700

Data Index: 5128720 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3857. Min Act: -0.1700

Data Index: 6377518 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.4107. Min Act: -0.1700

Data Index: 3182482 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3693. Min Act: -0.1700

Data Index: 7053330 (Open Web Text)

Max Activating Token Index: 720

Text #7

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3902. Min Act: -0.1700

Data Index: 557913 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3820. Min Act: -0.1700

Data Index: 1331960 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.4134. Min Act: -0.1700

Data Index: 4494336 (Open Web Text)

Max Activating Token Index: 155

Text #10

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3509. Min Act: -0.1700

Data Index: 7596304 (Open Web Text)

Max Activating Token Index: 958

Text #11

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3403. Min Act: -0.1700

Data Index: 7204084 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3536. Min Act: -0.1700

Data Index: 4165634 (Open Web Text)

Max Activating Token Index: 813

Text #13

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3608. Min Act: -0.1700

Data Index: 1439039 (Open Web Text)

Max Activating Token Index: 776

Text #14

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3492. Min Act: -0.1700

Data Index: 3746410 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3159. Min Act: -0.1700

Data Index: 927469 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3175. Min Act: -0.1700

Data Index: 2923269 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3169. Min Act: -0.1700

Data Index: 690366 (Open Web Text)

Max Activating Token Index: 906

Text #18

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.3092. Min Act: -0.1700

Data Index: 4544541 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 3.8065. Min Range: -3.8065

Max Act: 3.2932. Min Act: -0.1700

Data Index: 2805287 (Open Web Text)

Max Activating Token Index: 591