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

Dataset: Open Web Text

Neuron 780 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: 0.3509. Min Range: -0.3509

Max Act: 0.3509. Min Act: -0.1698

Data Index: 4727379 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3457. Min Act: -0.1659

Data Index: 6591865 (Open Web Text)

Max Activating Token Index: 804

Text #2

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3333. Min Act: -0.1677

Data Index: 3676702 (Open Web Text)

Max Activating Token Index: 1002

Text #3

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3157. Min Act: -0.1697

Data Index: 7094936 (Open Web Text)

Max Activating Token Index: 69

Text #4

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3136. Min Act: -0.1700

Data Index: 3899492 (Open Web Text)

Max Activating Token Index: 590

Text #5

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2991. Min Act: -0.1690

Data Index: 246502 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3056. Min Act: -0.1700

Data Index: 3835814 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2976. Min Act: -0.1686

Data Index: 412294 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3003. Min Act: -0.1677

Data Index: 3315229 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2918. Min Act: -0.1679

Data Index: 3031146 (Open Web Text)

Max Activating Token Index: 852

Text #10

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2946. Min Act: -0.1666

Data Index: 2849082 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2926. Min Act: -0.1677

Data Index: 4739355 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2936. Min Act: -0.1672

Data Index: 3847234 (Open Web Text)

Max Activating Token Index: 316

Text #13

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2883. Min Act: -0.1690

Data Index: 8572101 (Open Web Text)

Max Activating Token Index: 614

Text #14

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2826. Min Act: -0.1696

Data Index: 6702295 (Open Web Text)

Max Activating Token Index: 794

Text #15

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2914. Min Act: -0.1700

Data Index: 4347739 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2725. Min Act: -0.1571

Data Index: 8765243 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2763. Min Act: -0.1550

Data Index: 3725164 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2821. Min Act: -0.1700

Data Index: 2384809 (Open Web Text)

Max Activating Token Index: 416

Text #19

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2779. Min Act: -0.1695

Data Index: 6268615 (Open Web Text)

Max Activating Token Index: 684