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

Dataset: Open Web Text

Neuron 2910 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: 1.7645. Min Range: -1.7645

Max Act: 1.7645. Min Act: -0.1697

Data Index: 6784206 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7326. Min Act: -0.1700

Data Index: 6184966 (Open Web Text)

Max Activating Token Index: 586

Text #2

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7227. Min Act: -0.1693

Data Index: 5715096 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7203. Min Act: -0.1700

Data Index: 7480137 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7209. Min Act: -0.1656

Data Index: 1462078 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7083. Min Act: -0.1700

Data Index: 2980491 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7185. Min Act: -0.1700

Data Index: 2898477 (Open Web Text)

Max Activating Token Index: 902

Text #7

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7166. Min Act: -0.1699

Data Index: 8601097 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7108. Min Act: -0.1700

Data Index: 7093550 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7260. Min Act: -0.1697

Data Index: 7124422 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6999. Min Act: -0.1699

Data Index: 1626511 (Open Web Text)

Max Activating Token Index: 878

Text #11

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6972. Min Act: -0.1695

Data Index: 4950454 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6974. Min Act: -0.1700

Data Index: 1600755 (Open Web Text)

Max Activating Token Index: 663

Text #13

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6800. Min Act: -0.1431

Data Index: 7955163 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6751. Min Act: -0.1700

Data Index: 4327179 (Open Web Text)

Max Activating Token Index: 228

Text #15

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6879. Min Act: -0.1700

Data Index: 2332146 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6877. Min Act: -0.1700

Data Index: 2939184 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6758. Min Act: -0.1700

Data Index: 1067004 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6726. Min Act: -0.1676

Data Index: 3229284 (Open Web Text)

Max Activating Token Index: 250

Text #19

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.6878. Min Act: -0.1698

Data Index: 1680801 (Open Web Text)

Max Activating Token Index: 921