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

Dataset: Open Web Text

Neuron 2464 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: 3.5719. Min Range: -3.5719

Max Act: 3.5719. Min Act: -0.1700

Data Index: 5781655 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.5346. Min Act: -0.1700

Data Index: 5867058 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.5148. Min Act: -0.1700

Data Index: 2209916 (Open Web Text)

Max Activating Token Index: 407

Text #3

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4914. Min Act: -0.1700

Data Index: 2639775 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4891. Min Act: -0.1700

Data Index: 2171436 (Open Web Text)

Max Activating Token Index: 784

Text #5

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4758. Min Act: -0.1700

Data Index: 4389327 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4677. Min Act: -0.1700

Data Index: 4140622 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4809. Min Act: -0.1700

Data Index: 2938076 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4355. Min Act: -0.1700

Data Index: 1174032 (Open Web Text)

Max Activating Token Index: 262

Text #9

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4606. Min Act: -0.1700

Data Index: 8210042 (Open Web Text)

Max Activating Token Index: 275

Text #10

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4154. Min Act: -0.1700

Data Index: 4871924 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4540. Min Act: -0.1700

Data Index: 3772858 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4691. Min Act: -0.1700

Data Index: 2395637 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4667. Min Act: -0.1700

Data Index: 93126 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4194. Min Act: -0.1700

Data Index: 7290796 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4395. Min Act: -0.1700

Data Index: 7118047 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4505. Min Act: -0.1700

Data Index: 6485826 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4570. Min Act: -0.1700

Data Index: 3180235 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4549. Min Act: -0.1700

Data Index: 2583690 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 3.5719. Min Range: -3.5719

Max Act: 3.4065. Min Act: -0.1700

Data Index: 5459604 (Open Web Text)

Max Activating Token Index: 379