Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 2872 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.5000. Min Act: -0.1700

Data Index: 3304156 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.5000. Min Act: -0.1700

Data Index: 1507374 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.4688. Min Act: -0.1698

Data Index: 1633824 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.4375. Min Act: -0.1700

Data Index: 2538597 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.4375. Min Act: -0.1700

Data Index: 8796556 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.4375. Min Act: -0.1700

Data Index: 2105972 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3750. Min Act: -0.1700

Data Index: 3733674 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3750. Min Act: -0.1700

Data Index: 5981970 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3438. Min Act: -0.1700

Data Index: 6037897 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3750. Min Act: -0.1700

Data Index: 1334832 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3438. Min Act: -0.1700

Data Index: 283022 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3125. Min Act: -0.1700

Data Index: 6388785 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.3125. Min Act: -0.1700

Data Index: 568562 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2813. Min Act: -0.1700

Data Index: 5443721 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2813. Min Act: -0.1700

Data Index: 3066154 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2813. Min Act: -0.1698

Data Index: 1802206 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1700

Data Index: 4920030 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2813. Min Act: -0.1700

Data Index: 4524138 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2188. Min Act: -0.1700

Data Index: 4239310 (Open Web Text)

Max Activating Token Index: 885

Text #19

Max Range: 5.5000. Min Range: -5.5000

Max Act: 5.2500. Min Act: -0.1697

Data Index: 3718361 (Open Web Text)

Max Activating Token Index: 4