Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 713 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.8080. Min Act: -0.1700

Data Index: 3348861 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7767. Min Act: -0.1700

Data Index: 370760 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6672. Min Act: -0.1700

Data Index: 4821953 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6516. Min Act: -0.1700

Data Index: 485976 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6203. Min Act: -0.1700

Data Index: 3557371 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6046. Min Act: -0.1700

Data Index: 4298544 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6203. Min Act: -0.1700

Data Index: 1495099 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6046. Min Act: -0.1700

Data Index: 2128431 (Open Web Text)

Max Activating Token Index: 762

Text #8

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5890. Min Act: -0.1700

Data Index: 7511618 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6046. Min Act: -0.1700

Data Index: 2533129 (Open Web Text)

Max Activating Token Index: 833

Text #10

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5890. Min Act: -0.1700

Data Index: 3509173 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5890. Min Act: -0.1700

Data Index: 2341189 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5577. Min Act: -0.1700

Data Index: 239027 (Open Web Text)

Max Activating Token Index: 857

Text #13

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5577. Min Act: -0.1700

Data Index: 328307 (Open Web Text)

Max Activating Token Index: 544

Text #14

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5890. Min Act: -0.1700

Data Index: 8662762 (Open Web Text)

Max Activating Token Index: 230

Text #15

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5577. Min Act: -0.1700

Data Index: 7061910 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5264. Min Act: -0.1700

Data Index: 224475 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5264. Min Act: -0.1700

Data Index: 7847243 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5420. Min Act: -0.1700

Data Index: 5998448 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1821786 (Open Web Text)

Max Activating Token Index: 771