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

Dataset: Open Web Text

Neuron 829 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: 3.1302. Min Range: -3.1302

Max Act: 3.1302. Min Act: -0.1700

Data Index: 2236642 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 3.1302. Min Range: -3.1302

Max Act: 3.1157. Min Act: -0.1700

Data Index: 313141 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 3.1302. Min Range: -3.1302

Max Act: 3.0436. Min Act: -0.1700

Data Index: 3293411 (Open Web Text)

Max Activating Token Index: 595

Text #3

Max Range: 3.1302. Min Range: -3.1302

Max Act: 3.0046. Min Act: -0.1700

Data Index: 3837536 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9826. Min Act: -0.1700

Data Index: 5559659 (Open Web Text)

Max Activating Token Index: 854

Text #5

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9685. Min Act: -0.1700

Data Index: 1715270 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9584. Min Act: -0.1700

Data Index: 6091932 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9877. Min Act: -0.1700

Data Index: 6772839 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9603. Min Act: -0.1700

Data Index: 4342761 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9575. Min Act: -0.1700

Data Index: 6618028 (Open Web Text)

Max Activating Token Index: 219

Text #10

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9578. Min Act: -0.1700

Data Index: 885663 (Open Web Text)

Max Activating Token Index: 792

Text #11

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9445. Min Act: -0.1700

Data Index: 2598439 (Open Web Text)

Max Activating Token Index: 251

Text #12

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9298. Min Act: -0.1700

Data Index: 1219812 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9192. Min Act: -0.1700

Data Index: 7732690 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9079. Min Act: -0.1700

Data Index: 8551710 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.8451. Min Act: -0.1700

Data Index: 123370 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9353. Min Act: -0.1700

Data Index: 1015717 (Open Web Text)

Max Activating Token Index: 735

Text #17

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9353. Min Act: -0.1700

Data Index: 5438926 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9241. Min Act: -0.1700

Data Index: 527600 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 3.1302. Min Range: -3.1302

Max Act: 2.9226. Min Act: -0.1700

Data Index: 4216342 (Open Web Text)

Max Activating Token Index: 529