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

Dataset: Open Web Text

Neuron 635 in Layer 3

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: 3.4234. Min Range: -3.4234

Max Act: 3.4234. Min Act: -0.1700

Data Index: 7573251 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2659. Min Act: -0.1700

Data Index: 7330668 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2624. Min Act: -0.1700

Data Index: 7398948 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2468. Min Act: -0.1700

Data Index: 8072725 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2246. Min Act: -0.1700

Data Index: 3744806 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.2429. Min Act: -0.1700

Data Index: 8611276 (Open Web Text)

Max Activating Token Index: 576

Text #6

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1848. Min Act: -0.1700

Data Index: 4586473 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1641. Min Act: -0.1700

Data Index: 3642298 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1637. Min Act: -0.1700

Data Index: 1902949 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1497. Min Act: -0.1700

Data Index: 767816 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1561. Min Act: -0.1700

Data Index: 4118630 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1486. Min Act: -0.1700

Data Index: 8175271 (Open Web Text)

Max Activating Token Index: 386

Text #12

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1622. Min Act: -0.1700

Data Index: 4197237 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1372. Min Act: -0.1700

Data Index: 2201635 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1603. Min Act: -0.1700

Data Index: 5383172 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1554. Min Act: -0.1700

Data Index: 6057370 (Open Web Text)

Max Activating Token Index: 851

Text #16

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1537. Min Act: -0.1700

Data Index: 5344965 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1630. Min Act: -0.1700

Data Index: 2332191 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1462. Min Act: -0.1700

Data Index: 7473289 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 3.4234. Min Range: -3.4234

Max Act: 3.1042. Min Act: -0.1700

Data Index: 7921594 (Open Web Text)

Max Activating Token Index: 468