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

Dataset: Open Web Text

Neuron 1961 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: 4.5938. Min Range: -4.5938

Max Act: 4.5938. Min Act: -0.1700

Data Index: 4985736 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4631. Min Act: -0.1700

Data Index: 8289238 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4496. Min Act: -0.1700

Data Index: 4262672 (Open Web Text)

Max Activating Token Index: 297

Text #3

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4581. Min Act: -0.1700

Data Index: 4145598 (Open Web Text)

Max Activating Token Index: 280

Text #4

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4127. Min Act: -0.1700

Data Index: 6278505 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4013. Min Act: -0.1700

Data Index: 5905549 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4191. Min Act: -0.1700

Data Index: 2791312 (Open Web Text)

Max Activating Token Index: 863

Text #7

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4135. Min Act: -0.1700

Data Index: 412708 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.4225. Min Act: -0.1700

Data Index: 308963 (Open Web Text)

Max Activating Token Index: 130

Text #9

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3971. Min Act: -0.1700

Data Index: 6153345 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3813. Min Act: -0.1700

Data Index: 3734177 (Open Web Text)

Max Activating Token Index: 660

Text #11

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3789. Min Act: -0.1700

Data Index: 7561402 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3752. Min Act: -0.1700

Data Index: 5149741 (Open Web Text)

Max Activating Token Index: 588

Text #13

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3802. Min Act: -0.1700

Data Index: 3778236 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3986. Min Act: -0.1700

Data Index: 5038119 (Open Web Text)

Max Activating Token Index: 675

Text #15

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3699. Min Act: -0.1700

Data Index: 7455978 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3722. Min Act: -0.1700

Data Index: 6794785 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3668. Min Act: -0.1700

Data Index: 4420270 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3537. Min Act: -0.1700

Data Index: 1131731 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 4.5938. Min Range: -4.5938

Max Act: 4.3509. Min Act: -0.1700

Data Index: 1178331 (Open Web Text)

Max Activating Token Index: 878