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

Dataset: Open Web Text

Neuron 2798 in Layer 5

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: 3.9004. Min Range: -3.9004

Max Act: 3.9004. Min Act: -0.1700

Data Index: 1918564 (Open Web Text)

Max Activating Token Index: 163

Text #1

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.8395. Min Act: -0.1700

Data Index: 4377664 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.7299. Min Act: -0.1700

Data Index: 2168167 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.7048. Min Act: -0.1700

Data Index: 7207029 (Open Web Text)

Max Activating Token Index: 336

Text #4

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6821. Min Act: -0.1700

Data Index: 5038773 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6434. Min Act: -0.1700

Data Index: 432896 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1811465 (Open Web Text)

Max Activating Token Index: 931

Text #7

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6414. Min Act: -0.1700

Data Index: 7121340 (Open Web Text)

Max Activating Token Index: 867

Text #8

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6445. Min Act: -0.1700

Data Index: 3796314 (Open Web Text)

Max Activating Token Index: 449

Text #9

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5867. Min Act: -0.1700

Data Index: 4851473 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6185. Min Act: -0.1700

Data Index: 7405814 (Open Web Text)

Max Activating Token Index: 948

Text #11

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1147277 (Open Web Text)

Max Activating Token Index: 351

Text #12

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.6224. Min Act: -0.1700

Data Index: 2262454 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5715. Min Act: -0.1700

Data Index: 8120947 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5735. Min Act: -0.1700

Data Index: 2084277 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5913. Min Act: -0.1700

Data Index: 7989684 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5979. Min Act: -0.1700

Data Index: 7855545 (Open Web Text)

Max Activating Token Index: 523

Text #17

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5850. Min Act: -0.1700

Data Index: 7660395 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5915. Min Act: -0.1700

Data Index: 4100944 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 3.9004. Min Range: -3.9004

Max Act: 3.5700. Min Act: -0.1700

Data Index: 6664297 (Open Web Text)

Max Activating Token Index: 1016