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

Dataset: Open Web Text

Neuron 1266 in Layer 2

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: 1.6388. Min Range: -1.6388

Max Act: 1.6388. Min Act: -0.1699

Data Index: 640502 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.6382. Min Act: -0.1700

Data Index: 92905 (Open Web Text)

Max Activating Token Index: 889

Text #2

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.6234. Min Act: -0.1700

Data Index: 4901468 (Open Web Text)

Max Activating Token Index: 62

Text #3

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.6167. Min Act: -0.1700

Data Index: 3494723 (Open Web Text)

Max Activating Token Index: 936

Text #4

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5898. Min Act: -0.1700

Data Index: 7322789 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5793. Min Act: -0.1700

Data Index: 2971240 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5700. Min Act: -0.1697

Data Index: 2719210 (Open Web Text)

Max Activating Token Index: 36

Text #7

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5490. Min Act: -0.1699

Data Index: 2236510 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5459. Min Act: -0.1696

Data Index: 1639108 (Open Web Text)

Max Activating Token Index: 59

Text #9

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5589. Min Act: -0.1700

Data Index: 7444146 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5547. Min Act: -0.1700

Data Index: 1522146 (Open Web Text)

Max Activating Token Index: 658

Text #11

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5564. Min Act: -0.1698

Data Index: 7892249 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5603. Min Act: -0.1696

Data Index: 8218023 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5543. Min Act: -0.1700

Data Index: 1179237 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5468. Min Act: -0.1700

Data Index: 1884664 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5520. Min Act: -0.1695

Data Index: 2593372 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5370. Min Act: -0.1700

Data Index: 2813600 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5433. Min Act: -0.1700

Data Index: 6558812 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5518. Min Act: -0.1700

Data Index: 7021598 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5384. Min Act: -0.1682

Data Index: 2059056 (Open Web Text)

Max Activating Token Index: 830