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

Dataset: Open Web Text

Neuron 2031 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: 4.2759. Min Range: -4.2759

Max Act: 4.2759. Min Act: -0.1700

Data Index: 4210403 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.1461. Min Act: -0.1700

Data Index: 3832182 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.1117. Min Act: -0.1700

Data Index: 5259394 (Open Web Text)

Max Activating Token Index: 919

Text #3

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.1238. Min Act: -0.1700

Data Index: 5555183 (Open Web Text)

Max Activating Token Index: 720

Text #4

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.0809. Min Act: -0.1700

Data Index: 5762439 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.0502. Min Act: -0.1700

Data Index: 1203587 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.0356. Min Act: -0.1700

Data Index: 5243837 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9656. Min Act: -0.1700

Data Index: 7118091 (Open Web Text)

Max Activating Token Index: 790

Text #8

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.0167. Min Act: -0.1700

Data Index: 3133942 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.0079. Min Act: -0.1700

Data Index: 5259368 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9858. Min Act: -0.1700

Data Index: 6765795 (Open Web Text)

Max Activating Token Index: 149

Text #11

Max Range: 4.2759. Min Range: -4.2759

Max Act: 4.0086. Min Act: -0.1700

Data Index: 5278921 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9558. Min Act: -0.1700

Data Index: 2403613 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9632. Min Act: -0.1700

Data Index: 3642862 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9521. Min Act: -0.1700

Data Index: 2548598 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9640. Min Act: -0.1700

Data Index: 5762425 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9641. Min Act: -0.1700

Data Index: 2272787 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9016. Min Act: -0.1700

Data Index: 1203588 (Open Web Text)

Max Activating Token Index: 358

Text #18

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.9214. Min Act: -0.1700

Data Index: 2453442 (Open Web Text)

Max Activating Token Index: 99

Text #19

Max Range: 4.2759. Min Range: -4.2759

Max Act: 3.8848. Min Act: -0.1700

Data Index: 1219041 (Open Web Text)

Max Activating Token Index: 776