Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.7467. Min Act: -0.1700

Data Index: 1663802 (Open Web Text)

Max Activating Token Index: 136

Text #1

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6985. Min Act: -0.1700

Data Index: 4711872 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.7049. Min Act: -0.1700

Data Index: 7603986 (Open Web Text)

Max Activating Token Index: 216

Text #3

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6741. Min Act: -0.1700

Data Index: 3854451 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6711. Min Act: -0.1700

Data Index: 4780139 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6446. Min Act: -0.1700

Data Index: 310035 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6536. Min Act: -0.1700

Data Index: 6890021 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6319. Min Act: -0.1700

Data Index: 1911688 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6216. Min Act: -0.1700

Data Index: 965043 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6268. Min Act: -0.1700

Data Index: 7942408 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6216. Min Act: -0.1700

Data Index: 1378098 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6226. Min Act: -0.1700

Data Index: 1188205 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6096. Min Act: -0.1700

Data Index: 8685542 (Open Web Text)

Max Activating Token Index: 951

Text #13

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6059. Min Act: -0.1700

Data Index: 1758467 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6053. Min Act: -0.1700

Data Index: 7860025 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6120. Min Act: -0.1700

Data Index: 2929594 (Open Web Text)

Max Activating Token Index: 139

Text #16

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.5976. Min Act: -0.1700

Data Index: 4980015 (Open Web Text)

Max Activating Token Index: 941

Text #17

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.6018. Min Act: -0.1700

Data Index: 8403455 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.5920. Min Act: -0.1700

Data Index: 1250020 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 2.7467. Min Range: -2.7467

Max Act: 2.5960. Min Act: -0.1700

Data Index: 3302422 (Open Web Text)

Max Activating Token Index: 979