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

Dataset: Open Web Text

Neuron 631 in Layer 0

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: 1.3178. Min Range: -1.3178

Max Act: 1.3142. Min Act: -0.1700

Data Index: 3502385 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.3178. Min Act: -0.1700

Data Index: 8703810 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.3076. Min Act: -0.1700

Data Index: 2797916 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2966. Min Act: -0.1700

Data Index: 421653 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2907. Min Act: -0.1700

Data Index: 6735357 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2918. Min Act: -0.1700

Data Index: 4871483 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2903. Min Act: -0.1700

Data Index: 4543872 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2929. Min Act: -0.1700

Data Index: 4399828 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2838. Min Act: -0.1700

Data Index: 8677096 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2834. Min Act: -0.1700

Data Index: 8390579 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2845. Min Act: -0.1700

Data Index: 6803205 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2794. Min Act: -0.1700

Data Index: 5920743 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2722. Min Act: -0.1700

Data Index: 6365532 (Open Web Text)

Max Activating Token Index: 547

Text #13

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2704. Min Act: -0.1700

Data Index: 3323276 (Open Web Text)

Max Activating Token Index: 547

Text #14

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2744. Min Act: -0.1700

Data Index: 6609985 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2746. Min Act: -0.1700

Data Index: 3634377 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2782. Min Act: -0.1700

Data Index: 5665406 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2772. Min Act: -0.1700

Data Index: 3092589 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2765. Min Act: -0.1700

Data Index: 1898033 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 1.3178. Min Range: -1.3178

Max Act: 1.2756. Min Act: -0.1700

Data Index: 7342355 (Open Web Text)

Max Activating Token Index: 564