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

Dataset: Open Web Text

Neuron 1377 in Layer 4

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: 3.3653. Min Range: -3.3653

Max Act: 3.3653. Min Act: -0.1700

Data Index: 4573038 (Open Web Text)

Max Activating Token Index: 631

Text #1

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.2496. Min Act: -0.1700

Data Index: 3827111 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.2252. Min Act: -0.1700

Data Index: 5199466 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1520. Min Act: -0.1700

Data Index: 3344411 (Open Web Text)

Max Activating Token Index: 603

Text #4

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1673. Min Act: -0.1700

Data Index: 6363851 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.1294. Min Act: -0.1700

Data Index: 209995 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0901. Min Act: -0.1700

Data Index: 139759 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0230. Min Act: -0.1700

Data Index: 4347818 (Open Web Text)

Max Activating Token Index: 598

Text #8

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0311. Min Act: -0.1700

Data Index: 3854709 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0505. Min Act: -0.1700

Data Index: 4877696 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0015. Min Act: -0.1700

Data Index: 7901167 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0195. Min Act: -0.1700

Data Index: 5255788 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.9928. Min Act: -0.1700

Data Index: 5643973 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 3.3653. Min Range: -3.3653

Max Act: 3.0167. Min Act: -0.1700

Data Index: 2580771 (Open Web Text)

Max Activating Token Index: 291

Text #14

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.9400. Min Act: -0.1700

Data Index: 795277 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.9266. Min Act: -0.1700

Data Index: 2320982 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.9435. Min Act: -0.1700

Data Index: 7891800 (Open Web Text)

Max Activating Token Index: 903

Text #17

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.9267. Min Act: -0.1700

Data Index: 2582872 (Open Web Text)

Max Activating Token Index: 117

Text #18

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.9325. Min Act: -0.1700

Data Index: 3752573 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 3.3653. Min Range: -3.3653

Max Act: 2.8947. Min Act: -0.1700

Data Index: 1073865 (Open Web Text)

Max Activating Token Index: 140