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

Dataset: Open Web Text

Neuron 4270 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.8080. Min Act: -0.1700

Data Index: 7555028 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.8080. Min Act: -0.1700

Data Index: 8049228 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6517. Min Act: -0.1700

Data Index: 704086 (Open Web Text)

Max Activating Token Index: 101

Text #3

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6517. Min Act: -0.1700

Data Index: 5268249 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6517. Min Act: -0.1700

Data Index: 8161760 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5892. Min Act: -0.1700

Data Index: 6318794 (Open Web Text)

Max Activating Token Index: 437

Text #6

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5580. Min Act: -0.1700

Data Index: 6997093 (Open Web Text)

Max Activating Token Index: 811

Text #7

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5267. Min Act: -0.1700

Data Index: 200230 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 6062626 (Open Web Text)

Max Activating Token Index: 197

Text #9

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 8512916 (Open Web Text)

Max Activating Token Index: 635

Text #10

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 1392427 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 7172904 (Open Web Text)

Max Activating Token Index: 856

Text #12

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 570970 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4642. Min Act: -0.1700

Data Index: 1810972 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4955. Min Act: -0.1700

Data Index: 5874393 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4642. Min Act: -0.1700

Data Index: 7541425 (Open Web Text)

Max Activating Token Index: 955

Text #16

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4017. Min Act: -0.1700

Data Index: 27376 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 6598872 (Open Web Text)

Max Activating Token Index: 586

Text #18

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.3705. Min Act: -0.1700

Data Index: 2930789 (Open Web Text)

Max Activating Token Index: 926

Text #19

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.4017. Min Act: -0.1700

Data Index: 3340228 (Open Web Text)

Max Activating Token Index: 331