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

Dataset: Open Web Text

Neuron 2337 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: 3.6508. Min Range: -3.6508

Max Act: 3.6441. Min Act: -0.1700

Data Index: 4607803 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.6295. Min Act: -0.1700

Data Index: 7639374 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.6207. Min Act: -0.1700

Data Index: 3857361 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.6508. Min Act: -0.1700

Data Index: 344651 (Open Web Text)

Max Activating Token Index: 804

Text #4

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.6116. Min Act: -0.1700

Data Index: 248397 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5909. Min Act: -0.1700

Data Index: 3319904 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5960. Min Act: -0.1700

Data Index: 3565356 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5544. Min Act: -0.1700

Data Index: 3968787 (Open Web Text)

Max Activating Token Index: 790

Text #8

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5431. Min Act: -0.1700

Data Index: 6425317 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5793. Min Act: -0.1700

Data Index: 3684058 (Open Web Text)

Max Activating Token Index: 1002

Text #10

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5423. Min Act: -0.1700

Data Index: 5872570 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5544. Min Act: -0.1700

Data Index: 1828834 (Open Web Text)

Max Activating Token Index: 803

Text #12

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5565. Min Act: -0.1700

Data Index: 7104301 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5581. Min Act: -0.1700

Data Index: 744551 (Open Web Text)

Max Activating Token Index: 607

Text #14

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5615. Min Act: -0.1700

Data Index: 5595849 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5285. Min Act: -0.1700

Data Index: 2783690 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5446. Min Act: -0.1700

Data Index: 5537282 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5289. Min Act: -0.1700

Data Index: 2684676 (Open Web Text)

Max Activating Token Index: 538

Text #18

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5230. Min Act: -0.1700

Data Index: 3609713 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5057. Min Act: -0.1700

Data Index: 5313703 (Open Web Text)

Max Activating Token Index: 993