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

Dataset: Open Web Text

Neuron 1894 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: 3.7016. Min Range: -3.7016

Max Act: 3.7016. Min Act: 0.0884

Data Index: 4140052 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6804. Min Act: -0.0590

Data Index: 218669 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6522. Min Act: 0.1344

Data Index: 6171597 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6314. Min Act: 0.0701

Data Index: 3654640 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6429. Min Act: -0.0144

Data Index: 6200775 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6420. Min Act: 0.0198

Data Index: 702865 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6402. Min Act: 0.2946

Data Index: 5069155 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6320. Min Act: 0.0032

Data Index: 3490191 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6191. Min Act: -0.0585

Data Index: 8180167 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.0915

Data Index: 3409592 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6091. Min Act: -0.1045

Data Index: 3971015 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: -0.0529

Data Index: 5023532 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: -0.0745

Data Index: 4811035 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.0171

Data Index: 5599922 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.1737

Data Index: 1029465 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: -0.0940

Data Index: 1620559 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.0957

Data Index: 4161753 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.1976

Data Index: 1635273 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.0617

Data Index: 2086705 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6000. Min Act: 0.1130

Data Index: 2121975 (Open Web Text)

Max Activating Token Index: 1