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

Dataset: Open Web Text

Neuron 251 in Layer 2

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: 3.9708. Min Range: -3.9708

Max Act: 3.9708. Min Act: -0.1700

Data Index: 5170326 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8957. Min Act: -0.1700

Data Index: 1981456 (Open Web Text)

Max Activating Token Index: 961

Text #2

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.9051. Min Act: -0.1700

Data Index: 8175283 (Open Web Text)

Max Activating Token Index: 191

Text #3

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8906. Min Act: -0.1700

Data Index: 8175282 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8458. Min Act: -0.1700

Data Index: 6496476 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8606. Min Act: -0.1700

Data Index: 129364 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8095. Min Act: -0.1700

Data Index: 1202459 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8292. Min Act: -0.1700

Data Index: 7989974 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7923. Min Act: -0.1700

Data Index: 7421056 (Open Web Text)

Max Activating Token Index: 993

Text #9

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7829. Min Act: -0.1700

Data Index: 8477494 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7955. Min Act: -0.1700

Data Index: 1403036 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.8126. Min Act: -0.1700

Data Index: 8244340 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7640. Min Act: -0.1700

Data Index: 5673271 (Open Web Text)

Max Activating Token Index: 823

Text #13

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7674. Min Act: -0.1700

Data Index: 7596615 (Open Web Text)

Max Activating Token Index: 295

Text #14

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7670. Min Act: -0.1700

Data Index: 4538153 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7792. Min Act: -0.1700

Data Index: 7558363 (Open Web Text)

Max Activating Token Index: 136

Text #16

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7744. Min Act: -0.1700

Data Index: 2625519 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7688. Min Act: -0.1700

Data Index: 116132 (Open Web Text)

Max Activating Token Index: 924

Text #18

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7534. Min Act: -0.1700

Data Index: 7124557 (Open Web Text)

Max Activating Token Index: 605

Text #19

Max Range: 3.9708. Min Range: -3.9708

Max Act: 3.7508. Min Act: -0.1700

Data Index: 6348378 (Open Web Text)

Max Activating Token Index: 938