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

Dataset: Open Web Text

Neuron 2086 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: 1.1010. Min Range: -1.1010

Max Act: 1.1010. Min Act: -0.1454

Data Index: 3817010 (Open Web Text)

Max Activating Token Index: 740

Text #1

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0849. Min Act: -0.1255

Data Index: 5927340 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0604. Min Act: -0.1643

Data Index: 270561 (Open Web Text)

Max Activating Token Index: 215

Text #3

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0409. Min Act: -0.1358

Data Index: 5209356 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0413. Min Act: -0.1671

Data Index: 6752348 (Open Web Text)

Max Activating Token Index: 698

Text #5

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0354. Min Act: -0.1674

Data Index: 4555666 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0360. Min Act: -0.1543

Data Index: 1824692 (Open Web Text)

Max Activating Token Index: 447

Text #7

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0332. Min Act: -0.1678

Data Index: 1810539 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0356. Min Act: -0.1398

Data Index: 1629472 (Open Web Text)

Max Activating Token Index: 634

Text #9

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0348. Min Act: -0.1663

Data Index: 7352564 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0206. Min Act: -0.1456

Data Index: 7502546 (Open Web Text)

Max Activating Token Index: 630

Text #11

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0280. Min Act: -0.1694

Data Index: 2338242 (Open Web Text)

Max Activating Token Index: 349

Text #12

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0225. Min Act: -0.1691

Data Index: 3627883 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0233. Min Act: -0.1524

Data Index: 6504830 (Open Web Text)

Max Activating Token Index: 715

Text #14

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0270. Min Act: -0.1437

Data Index: 2363732 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0296. Min Act: -0.1689

Data Index: 4662389 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0211. Min Act: -0.1578

Data Index: 5857413 (Open Web Text)

Max Activating Token Index: 110

Text #17

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0147. Min Act: -0.1408

Data Index: 900792 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0182. Min Act: -0.1639

Data Index: 522253 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 1.1010. Min Range: -1.1010

Max Act: 1.0191. Min Act: -0.1527

Data Index: 2587606 (Open Web Text)

Max Activating Token Index: 438