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

Dataset: Open Web Text

Neuron 1381 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: 3.3271. Min Range: -3.3271

Max Act: 3.3271. Min Act: -0.1700

Data Index: 6854947 (Open Web Text)

Max Activating Token Index: 511

Text #1

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.2306. Min Act: -0.1700

Data Index: 66287 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.2328. Min Act: -0.1700

Data Index: 5464578 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.2273. Min Act: -0.1700

Data Index: 247868 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.2306. Min Act: -0.1700

Data Index: 3279058 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.2324. Min Act: -0.1700

Data Index: 610130 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.2045. Min Act: -0.1700

Data Index: 1868714 (Open Web Text)

Max Activating Token Index: 470

Text #7

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1870. Min Act: -0.1700

Data Index: 266393 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1850. Min Act: -0.1700

Data Index: 1120855 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1746. Min Act: -0.1700

Data Index: 8626997 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1804. Min Act: -0.1700

Data Index: 183392 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1901. Min Act: -0.1700

Data Index: 8619007 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1870. Min Act: -0.1700

Data Index: 4152872 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1966. Min Act: -0.1700

Data Index: 5859628 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1650. Min Act: -0.1700

Data Index: 6046896 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1732. Min Act: -0.1700

Data Index: 6356137 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1715145 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1845. Min Act: -0.1700

Data Index: 2394641 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1760. Min Act: -0.1700

Data Index: 84631 (Open Web Text)

Max Activating Token Index: 259

Text #19

Max Range: 3.3271. Min Range: -3.3271

Max Act: 3.1491. Min Act: -0.1700

Data Index: 2886629 (Open Web Text)

Max Activating Token Index: 278