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

Dataset: Open Web Text

Neuron 1262 in Layer 1

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: 1.4923. Min Range: -1.4923

Max Act: 1.4923. Min Act: -0.1700

Data Index: 7903066 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4582. Min Act: -0.1700

Data Index: 6046328 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4587. Min Act: -0.1693

Data Index: 6907639 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4420. Min Act: -0.1700

Data Index: 7066129 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4469. Min Act: -0.1696

Data Index: 3530871 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4395. Min Act: -0.1694

Data Index: 519536 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4438. Min Act: -0.1700

Data Index: 1872397 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4284. Min Act: -0.1696

Data Index: 4998713 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4317. Min Act: -0.1700

Data Index: 5859818 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4282. Min Act: -0.1699

Data Index: 6440583 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4262. Min Act: -0.1691

Data Index: 6891912 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4239. Min Act: -0.1691

Data Index: 1641449 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4245. Min Act: -0.1700

Data Index: 6943508 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4253. Min Act: -0.1683

Data Index: 4437131 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4273. Min Act: -0.1700

Data Index: 3527798 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4239. Min Act: -0.1700

Data Index: 2021251 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4081. Min Act: -0.1700

Data Index: 1493634 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4131. Min Act: -0.1697

Data Index: 2314120 (Open Web Text)

Max Activating Token Index: 75

Text #18

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4166. Min Act: -0.1700

Data Index: 744878 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4168. Min Act: -0.1700

Data Index: 3881826 (Open Web Text)

Max Activating Token Index: 86