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

Dataset: Open Web Text

Neuron 3009 in Layer 1

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: 1.7047. Min Range: -1.7047

Max Act: 1.7047. Min Act: -0.1700

Data Index: 6118657 (Open Web Text)

Max Activating Token Index: 647

Text #1

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6541. Min Act: -0.1700

Data Index: 8476112 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6551. Min Act: -0.1700

Data Index: 6057985 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6338. Min Act: -0.1700

Data Index: 5222062 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6315. Min Act: -0.1700

Data Index: 918409 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6237. Min Act: -0.1700

Data Index: 4766335 (Open Web Text)

Max Activating Token Index: 616

Text #6

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6297. Min Act: -0.1700

Data Index: 527531 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6112. Min Act: -0.1700

Data Index: 3516308 (Open Web Text)

Max Activating Token Index: 537

Text #8

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6134. Min Act: -0.1700

Data Index: 6544877 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6242. Min Act: -0.1700

Data Index: 3444187 (Open Web Text)

Max Activating Token Index: 915

Text #10

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6025. Min Act: -0.1700

Data Index: 6823630 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.6002. Min Act: -0.1700

Data Index: 258691 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5918. Min Act: -0.1700

Data Index: 1973685 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5840. Min Act: -0.1700

Data Index: 7587865 (Open Web Text)

Max Activating Token Index: 225

Text #14

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5891. Min Act: -0.1700

Data Index: 4046878 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5737. Min Act: -0.1700

Data Index: 8506800 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5810. Min Act: -0.1700

Data Index: 8671700 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5763. Min Act: -0.1700

Data Index: 4834421 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5652. Min Act: -0.1700

Data Index: 616805 (Open Web Text)

Max Activating Token Index: 701

Text #19

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.5762. Min Act: -0.1700

Data Index: 6473637 (Open Web Text)

Max Activating Token Index: 467