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

Dataset: Open Web Text

Neuron 2978 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: 4.0695. Min Range: -4.0695

Max Act: 4.0695. Min Act: -0.1700

Data Index: 8759572 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 4.0695. Min Range: -4.0695

Max Act: 4.0448. Min Act: -0.1700

Data Index: 1662285 (Open Web Text)

Max Activating Token Index: 87

Text #2

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.9935. Min Act: -0.1700

Data Index: 2858917 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.9256. Min Act: -0.1700

Data Index: 8792384 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.9068. Min Act: -0.1700

Data Index: 2858913 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8358. Min Act: -0.1700

Data Index: 8759559 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8382. Min Act: -0.1700

Data Index: 980430 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8357. Min Act: -0.1700

Data Index: 4142712 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7914. Min Act: -0.1700

Data Index: 3374996 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8149. Min Act: -0.1700

Data Index: 3923779 (Open Web Text)

Max Activating Token Index: 742

Text #10

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7731. Min Act: -0.1700

Data Index: 1033781 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7870. Min Act: -0.1700

Data Index: 4054005 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7383. Min Act: -0.1700

Data Index: 2858918 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7347. Min Act: -0.1700

Data Index: 3136890 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7267. Min Act: -0.1700

Data Index: 8759569 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1353551 (Open Web Text)

Max Activating Token Index: 122

Text #16

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7699. Min Act: -0.1700

Data Index: 2858910 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7634. Min Act: -0.1700

Data Index: 3917266 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.6974. Min Act: -0.1700

Data Index: 2858912 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7008. Min Act: -0.1700

Data Index: 8759553 (Open Web Text)

Max Activating Token Index: 715