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

Dataset: Open Web Text

Neuron 108 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: 4.7606. Min Range: -4.7606

Max Act: 4.7603. Min Act: -0.1700

Data Index: 7906426 (Open Web Text)

Max Activating Token Index: 226

Text #1

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.7409. Min Act: -0.1700

Data Index: 211074 (Open Web Text)

Max Activating Token Index: 847

Text #2

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.7606. Min Act: -0.1700

Data Index: 226299 (Open Web Text)

Max Activating Token Index: 348

Text #3

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.7415. Min Act: -0.1700

Data Index: 3313272 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6926. Min Act: -0.1700

Data Index: 5207189 (Open Web Text)

Max Activating Token Index: 667

Text #5

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6994. Min Act: -0.1700

Data Index: 7724257 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6819. Min Act: -0.1700

Data Index: 226300 (Open Web Text)

Max Activating Token Index: 257

Text #7

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6977. Min Act: -0.1700

Data Index: 7635181 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6810. Min Act: -0.1700

Data Index: 20975 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6851. Min Act: -0.1700

Data Index: 4934129 (Open Web Text)

Max Activating Token Index: 646

Text #10

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6797. Min Act: -0.1700

Data Index: 4026319 (Open Web Text)

Max Activating Token Index: 719

Text #11

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6125. Min Act: -0.1700

Data Index: 1492815 (Open Web Text)

Max Activating Token Index: 124

Text #12

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6738. Min Act: -0.1700

Data Index: 1661519 (Open Web Text)

Max Activating Token Index: 498

Text #13

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6288. Min Act: -0.1700

Data Index: 330181 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.5876. Min Act: -0.1700

Data Index: 596492 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6446. Min Act: -0.1700

Data Index: 3566982 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6698. Min Act: -0.1700

Data Index: 4539069 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6121. Min Act: -0.1700

Data Index: 818501 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6055. Min Act: -0.1700

Data Index: 3699257 (Open Web Text)

Max Activating Token Index: 1018

Text #19

Max Range: 4.7606. Min Range: -4.7606

Max Act: 4.6018. Min Act: -0.1700

Data Index: 243547 (Open Web Text)

Max Activating Token Index: 694