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

Dataset: Open Web Text

Neuron 966 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: 4.5618. Min Range: -4.5618

Max Act: 4.5618. Min Act: -0.1700

Data Index: 252648 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.5425. Min Act: -0.1700

Data Index: 5868011 (Open Web Text)

Max Activating Token Index: 366

Text #2

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.5024. Min Act: -0.1700

Data Index: 7186631 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4911. Min Act: -0.1700

Data Index: 315792 (Open Web Text)

Max Activating Token Index: 356

Text #4

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4928. Min Act: -0.1700

Data Index: 4833925 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4631. Min Act: -0.1700

Data Index: 1836359 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.5163. Min Act: -0.1700

Data Index: 4002014 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4820. Min Act: -0.1700

Data Index: 4539527 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4753. Min Act: -0.1700

Data Index: 1747195 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4852. Min Act: -0.1700

Data Index: 4025982 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4991. Min Act: -0.1700

Data Index: 5526765 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.5174. Min Act: -0.1700

Data Index: 195664 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4660. Min Act: -0.1700

Data Index: 344482 (Open Web Text)

Max Activating Token Index: 983

Text #13

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4213. Min Act: -0.1700

Data Index: 6908617 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4178. Min Act: -0.1700

Data Index: 1778338 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4395. Min Act: -0.1700

Data Index: 6791275 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4432. Min Act: -0.1700

Data Index: 7914137 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4315. Min Act: -0.1700

Data Index: 5145539 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.4213. Min Act: -0.1700

Data Index: 5288241 (Open Web Text)

Max Activating Token Index: 268

Text #19

Max Range: 4.5618. Min Range: -4.5618

Max Act: 4.3790. Min Act: -0.1700

Data Index: 48481 (Open Web Text)

Max Activating Token Index: 216