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

Dataset: Open Web Text

Neuron 2674 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: 1.6714. Min Range: -1.6714

Max Act: 1.6714. Min Act: -0.1698

Data Index: 110241 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6322. Min Act: -0.1699

Data Index: 3557872 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6352. Min Act: -0.1700

Data Index: 8339304 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6248. Min Act: -0.1700

Data Index: 5797953 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6279. Min Act: -0.1700

Data Index: 7655442 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6239. Min Act: -0.1697

Data Index: 6739078 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6172. Min Act: -0.1695

Data Index: 3440115 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6188. Min Act: -0.1700

Data Index: 700688 (Open Web Text)

Max Activating Token Index: 177

Text #8

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6071. Min Act: -0.1700

Data Index: 8559903 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6098. Min Act: -0.1699

Data Index: 3683175 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6005. Min Act: -0.1698

Data Index: 6341685 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5977. Min Act: -0.1700

Data Index: 7016434 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5822. Min Act: -0.1700

Data Index: 5089745 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5931. Min Act: -0.1688

Data Index: 3966930 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5956. Min Act: -0.1698

Data Index: 4717111 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5979. Min Act: -0.1700

Data Index: 4228322 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5849. Min Act: -0.1700

Data Index: 240054 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5825. Min Act: -0.1700

Data Index: 6214527 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5845. Min Act: -0.1698

Data Index: 4936929 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5714. Min Act: -0.1700

Data Index: 5891079 (Open Web Text)

Max Activating Token Index: 377