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

Dataset: Open Web Text

Neuron 2031 in Layer 6

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: 3.0752. Min Range: -3.0752

Max Act: 3.0752. Min Act: -0.1700

Data Index: 1817635 (Open Web Text)

Max Activating Token Index: 568

Text #1

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0578. Min Act: -0.1700

Data Index: 437227 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1319974 (Open Web Text)

Max Activating Token Index: 716

Text #3

Max Range: 3.0752. Min Range: -3.0752

Max Act: 3.0064. Min Act: -0.1700

Data Index: 1134782 (Open Web Text)

Max Activating Token Index: 625

Text #4

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9955. Min Act: -0.1700

Data Index: 894418 (Open Web Text)

Max Activating Token Index: 318

Text #5

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9677. Min Act: -0.1700

Data Index: 4450818 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9772. Min Act: -0.1700

Data Index: 5591372 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9625. Min Act: -0.1700

Data Index: 7172562 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9659. Min Act: -0.1700

Data Index: 3382787 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9631. Min Act: -0.1700

Data Index: 4131817 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9373. Min Act: -0.1700

Data Index: 2505549 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9496. Min Act: -0.1700

Data Index: 5591374 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9169. Min Act: -0.1700

Data Index: 1442767 (Open Web Text)

Max Activating Token Index: 864

Text #13

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9148. Min Act: -0.1700

Data Index: 934800 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9217. Min Act: -0.1700

Data Index: 6041847 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9008. Min Act: -0.1700

Data Index: 2964303 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.9203. Min Act: -0.1700

Data Index: 6980772 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.8944. Min Act: -0.1700

Data Index: 5340571 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.8724. Min Act: -0.1700

Data Index: 3968258 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 3.0752. Min Range: -3.0752

Max Act: 2.8890. Min Act: -0.1700

Data Index: 1887242 (Open Web Text)

Max Activating Token Index: 171