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

Dataset: Open Web Text

Neuron 2242 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: 3.9963. Min Range: -3.9963

Max Act: 3.9567. Min Act: -0.1700

Data Index: 750655 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9963. Min Act: -0.1700

Data Index: 5959991 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9717. Min Act: -0.1700

Data Index: 8490389 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9824. Min Act: -0.1700

Data Index: 7065652 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9407. Min Act: -0.1700

Data Index: 8175082 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9289. Min Act: -0.1700

Data Index: 4417003 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9378. Min Act: -0.1700

Data Index: 1919155 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9030. Min Act: -0.1700

Data Index: 6683700 (Open Web Text)

Max Activating Token Index: 805

Text #8

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8894. Min Act: -0.1700

Data Index: 2565533 (Open Web Text)

Max Activating Token Index: 739

Text #9

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8849. Min Act: -0.1700

Data Index: 8669399 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8913. Min Act: -0.1700

Data Index: 8259862 (Open Web Text)

Max Activating Token Index: 368

Text #11

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9088. Min Act: -0.1700

Data Index: 1193709 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8983. Min Act: -0.1700

Data Index: 2355089 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8885. Min Act: -0.1700

Data Index: 2351667 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9085. Min Act: -0.1700

Data Index: 6870596 (Open Web Text)

Max Activating Token Index: 676

Text #15

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8510. Min Act: -0.1700

Data Index: 6010342 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8558. Min Act: -0.1700

Data Index: 6324309 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9160. Min Act: -0.1700

Data Index: 6462413 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.9087. Min Act: -0.1700

Data Index: 3031079 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.9963. Min Range: -3.9963

Max Act: 3.8547. Min Act: -0.1700

Data Index: 6815682 (Open Web Text)

Max Activating Token Index: 946