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

Dataset: Open Web Text

Neuron 1083 in Layer 44

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.8080. Min Act: -0.1700

Data Index: 7735362 (Open Web Text)

Max Activating Token Index: 521

Text #1

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 7760280 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5267. Min Act: -0.1700

Data Index: 3745483 (Open Web Text)

Max Activating Token Index: 839

Text #3

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 4250081 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 6902737 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3392. Min Act: -0.1700

Data Index: 8577203 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1517. Min Act: -0.1700

Data Index: 8775801 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1205. Min Act: -0.1700

Data Index: 5108883 (Open Web Text)

Max Activating Token Index: 847

Text #8

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.1205. Min Act: -0.1700

Data Index: 394880 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0892. Min Act: -0.1700

Data Index: 61267 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0892. Min Act: -0.1700

Data Index: 6902736 (Open Web Text)

Max Activating Token Index: 867

Text #11

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0580. Min Act: -0.1700

Data Index: 2969283 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0267. Min Act: -0.1700

Data Index: 3340290 (Open Web Text)

Max Activating Token Index: 414

Text #13

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0267. Min Act: -0.1700

Data Index: 246176 (Open Web Text)

Max Activating Token Index: 409

Text #14

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.0267. Min Act: -0.1700

Data Index: 6484440 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9642. Min Act: -0.1700

Data Index: 6491704 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9955. Min Act: -0.1700

Data Index: 4527513 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9955. Min Act: -0.1700

Data Index: 7871229 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9642. Min Act: -0.1700

Data Index: 5971047 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 7.8080. Min Range: -7.8080

Max Act: 6.9642. Min Act: -0.1700

Data Index: 6566794 (Open Web Text)

Max Activating Token Index: 561