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

Dataset: Open Web Text

Neuron 3006 in Layer 3

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: 3.2781. Min Range: -3.2781

Max Act: 3.2695. Min Act: -0.1700

Data Index: 8507502 (Open Web Text)

Max Activating Token Index: 281

Text #1

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2402. Min Act: -0.1700

Data Index: 6851806 (Open Web Text)

Max Activating Token Index: 878

Text #2

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1727. Min Act: -0.1700

Data Index: 5107588 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2781. Min Act: -0.1700

Data Index: 2962519 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1576. Min Act: -0.1700

Data Index: 1871797 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2531. Min Act: -0.1700

Data Index: 4552718 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1998. Min Act: -0.1700

Data Index: 239188 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1979. Min Act: -0.1700

Data Index: 5161520 (Open Web Text)

Max Activating Token Index: 158

Text #8

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1861. Min Act: -0.1700

Data Index: 6679021 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1980. Min Act: -0.1700

Data Index: 1675597 (Open Web Text)

Max Activating Token Index: 998

Text #10

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2103. Min Act: -0.1700

Data Index: 6940843 (Open Web Text)

Max Activating Token Index: 830

Text #11

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1642. Min Act: -0.1700

Data Index: 6698614 (Open Web Text)

Max Activating Token Index: 675

Text #12

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1617. Min Act: -0.1700

Data Index: 1150875 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1274236 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.0734. Min Act: -0.1700

Data Index: 3193481 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.0947. Min Act: -0.1700

Data Index: 6771996 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1434. Min Act: -0.1700

Data Index: 439994 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.0733. Min Act: -0.1700

Data Index: 1375968 (Open Web Text)

Max Activating Token Index: 786

Text #18

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.0967. Min Act: -0.1700

Data Index: 916342 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.0969. Min Act: -0.1700

Data Index: 2044230 (Open Web Text)

Max Activating Token Index: 603