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

Dataset: Open Web Text

Neuron 871 in Layer 0

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: 4.7024. Min Range: -4.7024

Max Act: 4.7024. Min Act: -0.1700

Data Index: 2390535 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6328. Min Act: -0.1700

Data Index: 2514094 (Open Web Text)

Max Activating Token Index: 647

Text #2

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6313. Min Act: -0.1700

Data Index: 2348880 (Open Web Text)

Max Activating Token Index: 732

Text #3

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6399. Min Act: -0.1700

Data Index: 5834579 (Open Web Text)

Max Activating Token Index: 766

Text #4

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6444. Min Act: -0.1700

Data Index: 4103785 (Open Web Text)

Max Activating Token Index: 672

Text #5

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5992. Min Act: -0.1700

Data Index: 8394555 (Open Web Text)

Max Activating Token Index: 966

Text #6

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5943. Min Act: -0.1700

Data Index: 6217612 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6350. Min Act: -0.1700

Data Index: 7511249 (Open Web Text)

Max Activating Token Index: 702

Text #8

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6011. Min Act: -0.1700

Data Index: 7920679 (Open Web Text)

Max Activating Token Index: 723

Text #9

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6319. Min Act: -0.1700

Data Index: 3735099 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5779. Min Act: -0.1700

Data Index: 5784150 (Open Web Text)

Max Activating Token Index: 948

Text #11

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5914. Min Act: -0.1700

Data Index: 1985579 (Open Web Text)

Max Activating Token Index: 726

Text #12

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5917. Min Act: -0.1700

Data Index: 7972100 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5869. Min Act: -0.1700

Data Index: 2350448 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5826. Min Act: -0.1700

Data Index: 3630704 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5750. Min Act: -0.1700

Data Index: 6168901 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5842. Min Act: -0.1700

Data Index: 6205237 (Open Web Text)

Max Activating Token Index: 768

Text #17

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5615. Min Act: -0.1700

Data Index: 1932197 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.6001. Min Act: -0.1700

Data Index: 8605236 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 4.7024. Min Range: -4.7024

Max Act: 4.5602. Min Act: -0.1700

Data Index: 7748878 (Open Web Text)

Max Activating Token Index: 744