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

Dataset: Open Web Text

Neuron 2262 in Layer 5

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: 3.1649. Min Range: -3.1649

Max Act: 3.1649. Min Act: -0.1700

Data Index: 66652 (Open Web Text)

Max Activating Token Index: 205

Text #1

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.1309. Min Act: -0.1700

Data Index: 897423 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.1282. Min Act: -0.1700

Data Index: 3242882 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0875. Min Act: -0.1700

Data Index: 3636755 (Open Web Text)

Max Activating Token Index: 781

Text #4

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0695. Min Act: -0.1700

Data Index: 4910492 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0612. Min Act: -0.1700

Data Index: 4911694 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0798. Min Act: -0.1700

Data Index: 8269513 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0655. Min Act: -0.1700

Data Index: 4893121 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0647. Min Act: -0.1700

Data Index: 4889517 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0573. Min Act: -0.1700

Data Index: 6835592 (Open Web Text)

Max Activating Token Index: 158

Text #10

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0447. Min Act: -0.1700

Data Index: 3360178 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0597. Min Act: -0.1700

Data Index: 4578198 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0552. Min Act: -0.1700

Data Index: 7781712 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0543. Min Act: -0.1700

Data Index: 6874641 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0419. Min Act: -0.1700

Data Index: 3990918 (Open Web Text)

Max Activating Token Index: 333

Text #15

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0484. Min Act: -0.1700

Data Index: 423560 (Open Web Text)

Max Activating Token Index: 561

Text #16

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0275. Min Act: -0.1700

Data Index: 6278443 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0470. Min Act: -0.1700

Data Index: 193 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0467. Min Act: -0.1700

Data Index: 7141651 (Open Web Text)

Max Activating Token Index: 335

Text #19

Max Range: 3.1649. Min Range: -3.1649

Max Act: 3.0500. Min Act: -0.1700

Data Index: 643517 (Open Web Text)

Max Activating Token Index: 155