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

Dataset: Open Web Text

Neuron 1687 in Layer 1

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: 1.8422. Min Range: -1.8422

Max Act: 1.8340. Min Act: -0.1700

Data Index: 2968887 (Open Web Text)

Max Activating Token Index: 382

Text #1

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.8422. Min Act: -0.1700

Data Index: 3897041 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.8177. Min Act: -0.1700

Data Index: 6163386 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.8019. Min Act: -0.1700

Data Index: 2836274 (Open Web Text)

Max Activating Token Index: 1010

Text #4

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7973. Min Act: -0.1700

Data Index: 306594 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7917. Min Act: -0.1700

Data Index: 2686969 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7947. Min Act: -0.1700

Data Index: 6789870 (Open Web Text)

Max Activating Token Index: 928

Text #7

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7900. Min Act: -0.1700

Data Index: 5596545 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7845. Min Act: -0.1700

Data Index: 393627 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7872. Min Act: -0.1700

Data Index: 4359920 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7796. Min Act: -0.1700

Data Index: 7506385 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7813. Min Act: -0.1700

Data Index: 1591863 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7815. Min Act: -0.1700

Data Index: 2666377 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7693. Min Act: -0.1700

Data Index: 2577273 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7795. Min Act: -0.1700

Data Index: 962793 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7714. Min Act: -0.1700

Data Index: 1176147 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7654. Min Act: -0.1700

Data Index: 7999872 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7597. Min Act: -0.1700

Data Index: 3382321 (Open Web Text)

Max Activating Token Index: 822

Text #18

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7740. Min Act: -0.1700

Data Index: 2495893 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7717. Min Act: -0.1700

Data Index: 8328702 (Open Web Text)

Max Activating Token Index: 892