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

Dataset: Open Web Text

Neuron 1533 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: 1.5770. Min Range: -1.5770

Max Act: 1.5770. Min Act: -0.1700

Data Index: 5795170 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5753. Min Act: -0.1693

Data Index: 4506988 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5461. Min Act: -0.1700

Data Index: 6243678 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5506. Min Act: -0.1700

Data Index: 8505278 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5503. Min Act: -0.1700

Data Index: 8532990 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5449. Min Act: -0.1648

Data Index: 4251609 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5362. Min Act: -0.1690

Data Index: 8138097 (Open Web Text)

Max Activating Token Index: 778

Text #7

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5357. Min Act: -0.1687

Data Index: 1659770 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5367. Min Act: -0.1700

Data Index: 4186134 (Open Web Text)

Max Activating Token Index: 26

Text #9

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5242. Min Act: -0.1698

Data Index: 1801200 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5319. Min Act: -0.1685

Data Index: 4223209 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5263. Min Act: -0.1680

Data Index: 8169821 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5248. Min Act: -0.1692

Data Index: 3545792 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5238. Min Act: -0.1650

Data Index: 3258677 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5163. Min Act: -0.1700

Data Index: 489073 (Open Web Text)

Max Activating Token Index: 666

Text #15

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5225. Min Act: -0.1671

Data Index: 191879 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5200. Min Act: -0.1698

Data Index: 2098561 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5212. Min Act: -0.1700

Data Index: 8362889 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5193. Min Act: -0.1663

Data Index: 6111340 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 1.5770. Min Range: -1.5770

Max Act: 1.5230. Min Act: -0.1693

Data Index: 820994 (Open Web Text)

Max Activating Token Index: 20