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

Dataset: Open Web Text

Neuron 2333 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: 2.8880. Min Range: -2.8880

Max Act: 2.8880. Min Act: -0.1700

Data Index: 7513901 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.8129. Min Act: -0.1700

Data Index: 7914144 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.8210. Min Act: -0.1700

Data Index: 2887226 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.8236. Min Act: -0.1700

Data Index: 7768478 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7888. Min Act: -0.1700

Data Index: 3600034 (Open Web Text)

Max Activating Token Index: 459

Text #5

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7772. Min Act: -0.1700

Data Index: 6564092 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.8021. Min Act: -0.1700

Data Index: 4977043 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7874. Min Act: -0.1700

Data Index: 5033769 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7926. Min Act: -0.1700

Data Index: 7807518 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.8072. Min Act: -0.1700

Data Index: 5246631 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7762. Min Act: -0.1700

Data Index: 1130509 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7822. Min Act: -0.1700

Data Index: 936588 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7874. Min Act: -0.1700

Data Index: 1540406 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7693. Min Act: -0.1700

Data Index: 8228419 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7797. Min Act: -0.1700

Data Index: 2018264 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7525. Min Act: -0.1700

Data Index: 3363387 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7487. Min Act: -0.1700

Data Index: 5475170 (Open Web Text)

Max Activating Token Index: 834

Text #17

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7473. Min Act: -0.1700

Data Index: 5953887 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7305. Min Act: -0.1700

Data Index: 5242862 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 2.8880. Min Range: -2.8880

Max Act: 2.7355. Min Act: -0.1700

Data Index: 1907342 (Open Web Text)

Max Activating Token Index: 907