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

Dataset: Open Web Text

Neuron 3772 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.8398. Min Act: -0.1700

Data Index: 8081734 (Open Web Text)

Max Activating Token Index: 938

Text #1

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.6523. Min Act: -0.1700

Data Index: 2480295 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.6523. Min Act: -0.1700

Data Index: 6280018 (Open Web Text)

Max Activating Token Index: 801

Text #3

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.5273. Min Act: -0.1700

Data Index: 2853341 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.5898. Min Act: -0.1700

Data Index: 3202096 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.4961. Min Act: -0.1700

Data Index: 4035894 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.4961. Min Act: -0.1700

Data Index: 2995175 (Open Web Text)

Max Activating Token Index: 199

Text #7

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.4336. Min Act: -0.1700

Data Index: 7520451 (Open Web Text)

Max Activating Token Index: 741

Text #8

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.4023. Min Act: -0.1700

Data Index: 59742 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.4023. Min Act: -0.1700

Data Index: 7520450 (Open Web Text)

Max Activating Token Index: 936

Text #10

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.4336. Min Act: -0.1700

Data Index: 958353 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3398. Min Act: -0.1700

Data Index: 6555852 (Open Web Text)

Max Activating Token Index: 141

Text #12

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3711. Min Act: -0.1700

Data Index: 43968 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3711. Min Act: -0.1700

Data Index: 4293872 (Open Web Text)

Max Activating Token Index: 906

Text #14

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3711. Min Act: -0.1700

Data Index: 7507171 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3711. Min Act: -0.1700

Data Index: 2259178 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3711. Min Act: -0.1700

Data Index: 5269428 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3086. Min Act: -0.1700

Data Index: 5828745 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3398. Min Act: -0.1700

Data Index: 3147298 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3086. Min Act: -0.1700

Data Index: 7634069 (Open Web Text)

Max Activating Token Index: 759