Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 2283 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.7571. Min Act: -0.1700

Data Index: 1384723 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.6321. Min Act: -0.1700

Data Index: 6661481 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.5696. Min Act: -0.1700

Data Index: 3393863 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4759. Min Act: -0.1700

Data Index: 7892805 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4446. Min Act: -0.1700

Data Index: 893813 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4759. Min Act: -0.1700

Data Index: 4561626 (Open Web Text)

Max Activating Token Index: 797

Text #6

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 4110880 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4134. Min Act: -0.1700

Data Index: 2661643 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4134. Min Act: -0.1700

Data Index: 2785926 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.4134. Min Act: -0.1700

Data Index: 128791 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3509. Min Act: -0.1700

Data Index: 5832634 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 1180352 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3509. Min Act: -0.1700

Data Index: 2923151 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 1520665 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3821. Min Act: -0.1700

Data Index: 6059210 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3509. Min Act: -0.1700

Data Index: 3073762 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3509. Min Act: -0.1700

Data Index: 1552437 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3196. Min Act: -0.1700

Data Index: 3865511 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3509. Min Act: -0.1700

Data Index: 6501007 (Open Web Text)

Max Activating Token Index: 593

Text #19

Max Range: 5.7571. Min Range: -5.7571

Max Act: 5.3196. Min Act: -0.1700

Data Index: 4480542 (Open Web Text)

Max Activating Token Index: 527