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

Dataset: Open Web Text

Neuron 275 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: 3.7868. Min Range: -3.7868

Max Act: 3.7868. Min Act: -0.1700

Data Index: 4281418 (Open Web Text)

Max Activating Token Index: 741

Text #1

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.7310. Min Act: -0.1700

Data Index: 4750595 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6643. Min Act: -0.1700

Data Index: 7116601 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5792. Min Act: -0.1700

Data Index: 2181020 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6277. Min Act: -0.1700

Data Index: 2038141 (Open Web Text)

Max Activating Token Index: 848

Text #5

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6101. Min Act: -0.1700

Data Index: 4060799 (Open Web Text)

Max Activating Token Index: 625

Text #6

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6059. Min Act: -0.1700

Data Index: 7499871 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6073. Min Act: -0.1700

Data Index: 4540225 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5888. Min Act: -0.1700

Data Index: 7940075 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5507. Min Act: -0.1700

Data Index: 2975346 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5960. Min Act: -0.1700

Data Index: 5262843 (Open Web Text)

Max Activating Token Index: 733

Text #11

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5864. Min Act: -0.1700

Data Index: 7940077 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5707. Min Act: -0.1700

Data Index: 7310259 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6013. Min Act: -0.1700

Data Index: 7940078 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.6146. Min Act: -0.1700

Data Index: 836968 (Open Web Text)

Max Activating Token Index: 615

Text #15

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5698. Min Act: -0.1700

Data Index: 2773414 (Open Web Text)

Max Activating Token Index: 942

Text #16

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5777. Min Act: -0.1700

Data Index: 3261320 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5432. Min Act: -0.1700

Data Index: 1562537 (Open Web Text)

Max Activating Token Index: 494

Text #18

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5104. Min Act: -0.1700

Data Index: 2309421 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 3.7868. Min Range: -3.7868

Max Act: 3.5210. Min Act: -0.1700

Data Index: 7761843 (Open Web Text)

Max Activating Token Index: 508