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

Dataset: Open Web Text

Neuron 939 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: 3.3937. Min Range: -3.3937

Max Act: 3.3937. Min Act: -0.1700

Data Index: 5913263 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.3548. Min Act: -0.1700

Data Index: 4742220 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.3397. Min Act: -0.1700

Data Index: 3790865 (Open Web Text)

Max Activating Token Index: 555

Text #3

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.2061. Min Act: -0.1700

Data Index: 5260933 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.2168. Min Act: -0.1700

Data Index: 700611 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.2170. Min Act: -0.1700

Data Index: 2660593 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1867. Min Act: -0.1700

Data Index: 733544 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1681. Min Act: -0.1700

Data Index: 2058897 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.2267. Min Act: -0.1700

Data Index: 137701 (Open Web Text)

Max Activating Token Index: 783

Text #9

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1582. Min Act: -0.1700

Data Index: 764852 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1558. Min Act: -0.1700

Data Index: 8317810 (Open Web Text)

Max Activating Token Index: 791

Text #11

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1231. Min Act: -0.1700

Data Index: 7196735 (Open Web Text)

Max Activating Token Index: 822

Text #12

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1288. Min Act: -0.1700

Data Index: 7543728 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1372. Min Act: -0.1700

Data Index: 5390150 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1282. Min Act: -0.1700

Data Index: 2602464 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1288. Min Act: -0.1700

Data Index: 1169446 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0604. Min Act: -0.1700

Data Index: 3227963 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1609. Min Act: -0.1700

Data Index: 6290029 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1378. Min Act: -0.1700

Data Index: 7277839 (Open Web Text)

Max Activating Token Index: 518

Text #19

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0873. Min Act: -0.1700

Data Index: 3247361 (Open Web Text)

Max Activating Token Index: 12