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

Dataset: Open Web Text

Neuron 952 in Layer 2

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: 1.9549. Min Range: -1.9549

Max Act: 1.9549. Min Act: -0.1700

Data Index: 1844566 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9460. Min Act: -0.1700

Data Index: 7680854 (Open Web Text)

Max Activating Token Index: 864

Text #2

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9412. Min Act: -0.1700

Data Index: 7321917 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8994. Min Act: -0.1700

Data Index: 162699 (Open Web Text)

Max Activating Token Index: 932

Text #4

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9325. Min Act: -0.1700

Data Index: 8726032 (Open Web Text)

Max Activating Token Index: 877

Text #5

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9128. Min Act: -0.1700

Data Index: 1824602 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9161. Min Act: -0.1700

Data Index: 3257527 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9185. Min Act: -0.1700

Data Index: 7680830 (Open Web Text)

Max Activating Token Index: 586

Text #8

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9068. Min Act: -0.1700

Data Index: 3640196 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.9031. Min Act: -0.1700

Data Index: 702288 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8778. Min Act: -0.1700

Data Index: 7647463 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8726. Min Act: -0.1700

Data Index: 4922700 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8749. Min Act: -0.1700

Data Index: 2389137 (Open Web Text)

Max Activating Token Index: 221

Text #13

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8684. Min Act: -0.1700

Data Index: 2001820 (Open Web Text)

Max Activating Token Index: 408

Text #14

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8753. Min Act: -0.1700

Data Index: 3834304 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8605. Min Act: -0.1700

Data Index: 1260653 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8507. Min Act: -0.1700

Data Index: 4713742 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8669. Min Act: -0.1700

Data Index: 2085346 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8648. Min Act: -0.1700

Data Index: 6047225 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 1.9549. Min Range: -1.9549

Max Act: 1.8518. Min Act: -0.1700

Data Index: 5576282 (Open Web Text)

Max Activating Token Index: 652