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

Dataset: Open Web Text

Neuron 452 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: 1.8753. Min Range: -1.8753

Max Act: 1.8753. Min Act: -0.1700

Data Index: 6860941 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8549. Min Act: -0.1700

Data Index: 594931 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8637. Min Act: -0.1699

Data Index: 6912951 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8541. Min Act: -0.1700

Data Index: 5080867 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8601. Min Act: -0.1700

Data Index: 6916168 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8421. Min Act: -0.1700

Data Index: 210226 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8482. Min Act: -0.1697

Data Index: 4935515 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8422. Min Act: -0.1700

Data Index: 3254699 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8336. Min Act: -0.1700

Data Index: 8823636 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8346. Min Act: -0.1700

Data Index: 5716487 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8243. Min Act: -0.1699

Data Index: 8821877 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8263. Min Act: -0.1700

Data Index: 4272805 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8281. Min Act: -0.1700

Data Index: 4256296 (Open Web Text)

Max Activating Token Index: 257

Text #13

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8207. Min Act: -0.1700

Data Index: 5716477 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8141. Min Act: -0.1700

Data Index: 6312441 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8189. Min Act: -0.1700

Data Index: 2773834 (Open Web Text)

Max Activating Token Index: 32

Text #16

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8143. Min Act: -0.1699

Data Index: 5313108 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8167. Min Act: -0.1700

Data Index: 5225777 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8163. Min Act: -0.1700

Data Index: 237623 (Open Web Text)

Max Activating Token Index: 181

Text #19

Max Range: 1.8753. Min Range: -1.8753

Max Act: 1.8184. Min Act: -0.1700

Data Index: 2855316 (Open Web Text)

Max Activating Token Index: 5