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

Dataset: Open Web Text

Neuron 2976 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: 1.7299. Min Range: -1.7299

Max Act: 1.7294. Min Act: -0.1586

Data Index: 1854984 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.7299. Min Act: -0.1540

Data Index: 6063570 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.7290. Min Act: -0.0235

Data Index: 8363379 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.7126. Min Act: -0.1621

Data Index: 5710509 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6992. Min Act: -0.1331

Data Index: 3990623 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6905. Min Act: -0.0874

Data Index: 8265950 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6926. Min Act: -0.1508

Data Index: 1759919 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6941. Min Act: -0.1573

Data Index: 2906583 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6884. Min Act: -0.1205

Data Index: 1355978 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6831. Min Act: -0.1109

Data Index: 6434268 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6856. Min Act: -0.1700

Data Index: 3260392 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6707. Min Act: -0.1619

Data Index: 2323074 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6777. Min Act: -0.1569

Data Index: 7722825 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6768. Min Act: -0.1109

Data Index: 7111161 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6724. Min Act: -0.1551

Data Index: 3458508 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6810. Min Act: -0.1469

Data Index: 7072832 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6810. Min Act: -0.1412

Data Index: 622666 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6707. Min Act: -0.1365

Data Index: 3500917 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6705. Min Act: -0.1648

Data Index: 1355975 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 1.7299. Min Range: -1.7299

Max Act: 1.6641. Min Act: -0.1301

Data Index: 6436917 (Open Web Text)

Max Activating Token Index: 925