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

Dataset: Open Web Text

Neuron 1649 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: 3.0217. Min Range: -3.0217

Max Act: 2.9794. Min Act: -0.1700

Data Index: 613598 (Open Web Text)

Max Activating Token Index: 844

Text #1

Max Range: 3.0217. Min Range: -3.0217

Max Act: 3.0217. Min Act: -0.1700

Data Index: 7509871 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 3.0217. Min Range: -3.0217

Max Act: 3.0057. Min Act: -0.1700

Data Index: 796352 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 3.0217. Min Range: -3.0217

Max Act: 3.0020. Min Act: -0.1700

Data Index: 7246868 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9834. Min Act: -0.1700

Data Index: 7371569 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9716. Min Act: -0.1700

Data Index: 7423103 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9505. Min Act: -0.1700

Data Index: 1048392 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9375. Min Act: -0.1700

Data Index: 3437501 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9427. Min Act: -0.1700

Data Index: 3357790 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9257. Min Act: -0.1700

Data Index: 2651268 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9331. Min Act: -0.1700

Data Index: 7932553 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9360. Min Act: -0.1700

Data Index: 8353442 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9473. Min Act: -0.1700

Data Index: 374195 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9060. Min Act: -0.1700

Data Index: 2632355 (Open Web Text)

Max Activating Token Index: 887

Text #14

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9078. Min Act: -0.1700

Data Index: 4744249 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9056. Min Act: -0.1700

Data Index: 6676822 (Open Web Text)

Max Activating Token Index: 715

Text #16

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9106. Min Act: -0.1700

Data Index: 5062990 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9197. Min Act: -0.1700

Data Index: 8136199 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9204. Min Act: -0.1700

Data Index: 3266981 (Open Web Text)

Max Activating Token Index: 483

Text #19

Max Range: 3.0217. Min Range: -3.0217

Max Act: 2.9125. Min Act: -0.1700

Data Index: 6585647 (Open Web Text)

Max Activating Token Index: 322