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

Dataset: Open Web Text

Neuron 529 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: 4.1925. Min Range: -4.1925

Max Act: 4.1925. Min Act: -0.1700

Data Index: 3679078 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.1285. Min Act: -0.1700

Data Index: 6289675 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.1011. Min Act: -0.1700

Data Index: 56905 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.1290. Min Act: -0.1700

Data Index: 894069 (Open Web Text)

Max Activating Token Index: 144

Text #4

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0810. Min Act: -0.1700

Data Index: 8365097 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0714. Min Act: -0.1700

Data Index: 616835 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0081. Min Act: -0.1700

Data Index: 1314615 (Open Web Text)

Max Activating Token Index: 792

Text #7

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0497. Min Act: -0.1700

Data Index: 5041635 (Open Web Text)

Max Activating Token Index: 634

Text #8

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0960. Min Act: -0.1700

Data Index: 4098934 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9973. Min Act: -0.1700

Data Index: 390803 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 4.1925. Min Range: -4.1925

Max Act: 4.0146. Min Act: -0.1700

Data Index: 3834504 (Open Web Text)

Max Activating Token Index: 821

Text #11

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9867. Min Act: -0.1700

Data Index: 5148195 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9898. Min Act: -0.1700

Data Index: 3197235 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9322. Min Act: -0.1700

Data Index: 4440981 (Open Web Text)

Max Activating Token Index: 656

Text #14

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9847. Min Act: -0.1700

Data Index: 8317330 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9643. Min Act: -0.1700

Data Index: 1745437 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9992. Min Act: -0.1700

Data Index: 2785541 (Open Web Text)

Max Activating Token Index: 252

Text #17

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9583. Min Act: -0.1700

Data Index: 2477970 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9222. Min Act: -0.1700

Data Index: 5156720 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 4.1925. Min Range: -4.1925

Max Act: 3.9870. Min Act: -0.1700

Data Index: 5549815 (Open Web Text)

Max Activating Token Index: 219