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

Dataset: Open Web Text

Neuron 38 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: 0.9715. Min Range: -0.9715

Max Act: 0.9715. Min Act: -0.0779

Data Index: 910313 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9466. Min Act: -0.1074

Data Index: 3804241 (Open Web Text)

Max Activating Token Index: 715

Text #2

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9324. Min Act: -0.1131

Data Index: 5352033 (Open Web Text)

Max Activating Token Index: 696

Text #3

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9309. Min Act: -0.1056

Data Index: 7248592 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9336. Min Act: -0.1163

Data Index: 1238787 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9337. Min Act: -0.1142

Data Index: 4572246 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9299. Min Act: -0.0987

Data Index: 7573089 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9242. Min Act: -0.1387

Data Index: 7384571 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9220. Min Act: -0.0961

Data Index: 7660217 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9092. Min Act: -0.1320

Data Index: 4625643 (Open Web Text)

Max Activating Token Index: 634

Text #10

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8993. Min Act: -0.1185

Data Index: 7492400 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9012. Min Act: -0.1088

Data Index: 272584 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9057. Min Act: -0.1163

Data Index: 3303843 (Open Web Text)

Max Activating Token Index: 791

Text #13

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9106. Min Act: -0.1115

Data Index: 5886142 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.9028. Min Act: -0.1131

Data Index: 6853255 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8988. Min Act: -0.1253

Data Index: 5674484 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8899. Min Act: -0.1410

Data Index: 7660207 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8871. Min Act: -0.1067

Data Index: 7474697 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8949. Min Act: -0.1054

Data Index: 1798227 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8849. Min Act: -0.0831

Data Index: 595404 (Open Web Text)

Max Activating Token Index: 607