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

Dataset: Open Web Text

Neuron 2703 in Layer 3

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: 4.6864. Min Range: -4.6864

Max Act: 4.6864. Min Act: -0.1700

Data Index: 2307454 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6652. Min Act: -0.1700

Data Index: 4913005 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6645. Min Act: -0.1700

Data Index: 6451539 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6650. Min Act: -0.1700

Data Index: 3779381 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6713. Min Act: -0.1700

Data Index: 5290631 (Open Web Text)

Max Activating Token Index: 571

Text #5

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6490. Min Act: -0.1700

Data Index: 5027640 (Open Web Text)

Max Activating Token Index: 368

Text #6

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6161. Min Act: -0.1700

Data Index: 2645769 (Open Web Text)

Max Activating Token Index: 268

Text #7

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5923. Min Act: -0.1700

Data Index: 1397692 (Open Web Text)

Max Activating Token Index: 538

Text #8

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.6062. Min Act: -0.1700

Data Index: 4949833 (Open Web Text)

Max Activating Token Index: 306

Text #9

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5824. Min Act: -0.1700

Data Index: 3760246 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5918. Min Act: -0.1700

Data Index: 5841160 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5891. Min Act: -0.1700

Data Index: 5322909 (Open Web Text)

Max Activating Token Index: 351

Text #12

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5520. Min Act: -0.1700

Data Index: 4879255 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5615. Min Act: -0.1700

Data Index: 2569129 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5418. Min Act: -0.1700

Data Index: 174356 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5404. Min Act: -0.1700

Data Index: 4784388 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5056. Min Act: -0.1700

Data Index: 2296839 (Open Web Text)

Max Activating Token Index: 983

Text #17

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5269. Min Act: -0.1700

Data Index: 2772176 (Open Web Text)

Max Activating Token Index: 270

Text #18

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5485. Min Act: -0.1700

Data Index: 4569411 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 4.6864. Min Range: -4.6864

Max Act: 4.5680. Min Act: -0.1700

Data Index: 5222389 (Open Web Text)

Max Activating Token Index: 628