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

Dataset: Open Web Text

Neuron 2160 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: 3.4008. Min Range: -3.4008

Max Act: 3.4008. Min Act: -0.1700

Data Index: 3741919 (Open Web Text)

Max Activating Token Index: 591

Text #1

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.2803. Min Act: -0.1700

Data Index: 2950340 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.2526. Min Act: -0.1700

Data Index: 3795210 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1786. Min Act: -0.1700

Data Index: 1254777 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1147. Min Act: -0.1700

Data Index: 1386260 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1500. Min Act: -0.1700

Data Index: 325571 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1406. Min Act: -0.1700

Data Index: 4223295 (Open Web Text)

Max Activating Token Index: 941

Text #7

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1032. Min Act: -0.1700

Data Index: 3451008 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0915. Min Act: -0.1700

Data Index: 7579339 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0839. Min Act: -0.1700

Data Index: 1313704 (Open Web Text)

Max Activating Token Index: 749

Text #10

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0901. Min Act: -0.1700

Data Index: 6875185 (Open Web Text)

Max Activating Token Index: 689

Text #11

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0982. Min Act: -0.1700

Data Index: 3510774 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0972. Min Act: -0.1698

Data Index: 6421067 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0318. Min Act: -0.1700

Data Index: 3325336 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0770. Min Act: -0.1700

Data Index: 4809409 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0514. Min Act: -0.1700

Data Index: 3834179 (Open Web Text)

Max Activating Token Index: 549

Text #16

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0539. Min Act: -0.1700

Data Index: 8168452 (Open Web Text)

Max Activating Token Index: 942

Text #17

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0948. Min Act: -0.1700

Data Index: 5590526 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9866. Min Act: -0.1700

Data Index: 4061112 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0375. Min Act: -0.1700

Data Index: 7284095 (Open Web Text)

Max Activating Token Index: 714