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

Dataset: Open Web Text

Neuron 4692 in Layer 33

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: 6747608 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.7455. Min Act: -0.1700

Data Index: 3479452 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.6830. Min Act: -0.1700

Data Index: 1072877 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.6830. Min Act: -0.1700

Data Index: 4803233 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 7809298 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 370251 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 6467799 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 6036870 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 4471587 (Open Web Text)

Max Activating Token Index: 347

Text #9

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.5580. Min Act: -0.1700

Data Index: 8038800 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 6266755 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 42336 (Open Web Text)

Max Activating Token Index: 437

Text #12

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4955. Min Act: -0.1700

Data Index: 2116120 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 1707627 (Open Web Text)

Max Activating Token Index: 607

Text #14

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 3878900 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4017. Min Act: -0.1700

Data Index: 3772650 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4330. Min Act: -0.1700

Data Index: 6840874 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.4017. Min Act: -0.1700

Data Index: 7910590 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3705. Min Act: -0.1700

Data Index: 4656383 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 7.8080. Min Range: -7.8080

Max Act: 7.3705. Min Act: -0.1700

Data Index: 6829133 (Open Web Text)

Max Activating Token Index: 334