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

Dataset: Open Web Text

Neuron 1757 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: 3.8754. Min Range: -3.8754

Max Act: 3.8754. Min Act: -0.1700

Data Index: 5500708 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8483. Min Act: -0.1700

Data Index: 5142242 (Open Web Text)

Max Activating Token Index: 177

Text #2

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8722. Min Act: -0.1700

Data Index: 6217930 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8233. Min Act: -0.1700

Data Index: 558818 (Open Web Text)

Max Activating Token Index: 503

Text #4

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8444. Min Act: -0.1700

Data Index: 3895860 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8264. Min Act: -0.1700

Data Index: 6553664 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8085. Min Act: -0.1700

Data Index: 5008481 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7770. Min Act: -0.1700

Data Index: 7935526 (Open Web Text)

Max Activating Token Index: 216

Text #8

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8113. Min Act: -0.1700

Data Index: 5766119 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8011. Min Act: -0.1700

Data Index: 4125040 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.8095. Min Act: -0.1700

Data Index: 7466402 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7618. Min Act: -0.1700

Data Index: 5013016 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7695. Min Act: -0.1700

Data Index: 2982927 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7665. Min Act: -0.1700

Data Index: 4309213 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7888. Min Act: -0.1700

Data Index: 7099482 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7977. Min Act: -0.1700

Data Index: 163428 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7761. Min Act: -0.1700

Data Index: 1494489 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7686. Min Act: -0.1700

Data Index: 2138190 (Open Web Text)

Max Activating Token Index: 610

Text #18

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7790. Min Act: -0.1700

Data Index: 3882234 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 3.8754. Min Range: -3.8754

Max Act: 3.7397. Min Act: -0.1700

Data Index: 2956908 (Open Web Text)

Max Activating Token Index: 49