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

Dataset: Open Web Text

Neuron 2795 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: 1.7873. Min Range: -1.7873

Max Act: 1.7873. Min Act: -0.1658

Data Index: 8583714 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7722. Min Act: -0.1700

Data Index: 4719829 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7488. Min Act: -0.1535

Data Index: 4606313 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7410. Min Act: -0.1700

Data Index: 5627168 (Open Web Text)

Max Activating Token Index: 799

Text #4

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7414. Min Act: -0.1696

Data Index: 3381169 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7350. Min Act: -0.1604

Data Index: 6835620 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7311. Min Act: -0.1673

Data Index: 3067123 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7207. Min Act: -0.1689

Data Index: 7370594 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7259. Min Act: -0.1699

Data Index: 2363752 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7219. Min Act: -0.1693

Data Index: 3333063 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7257. Min Act: -0.1583

Data Index: 6863304 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7289. Min Act: -0.1677

Data Index: 5627169 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7128. Min Act: -0.1625

Data Index: 1482195 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7137. Min Act: -0.1696

Data Index: 6640552 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7214. Min Act: -0.1512

Data Index: 7015983 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7208. Min Act: -0.1583

Data Index: 7773491 (Open Web Text)

Max Activating Token Index: 32

Text #16

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7212. Min Act: -0.1683

Data Index: 2317180 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7132. Min Act: -0.1668

Data Index: 7089169 (Open Web Text)

Max Activating Token Index: 33

Text #18

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7064. Min Act: -0.1698

Data Index: 2264222 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 1.7873. Min Range: -1.7873

Max Act: 1.7071. Min Act: -0.1643

Data Index: 2401207 (Open Web Text)

Max Activating Token Index: 13