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

Dataset: Open Web Text

Neuron 1305 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: 3.2692. Min Range: -3.2692

Max Act: 3.2545. Min Act: -0.1700

Data Index: 7803081 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.2692. Min Act: -0.1700

Data Index: 4669469 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.2409. Min Act: -0.1700

Data Index: 5867496 (Open Web Text)

Max Activating Token Index: 264

Text #3

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.2410. Min Act: -0.1700

Data Index: 6912261 (Open Web Text)

Max Activating Token Index: 611

Text #4

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.2099. Min Act: -0.1700

Data Index: 2235694 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.2219. Min Act: -0.1700

Data Index: 4896800 (Open Web Text)

Max Activating Token Index: 184

Text #6

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1785. Min Act: -0.1700

Data Index: 5972431 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1745. Min Act: -0.1700

Data Index: 3959498 (Open Web Text)

Max Activating Token Index: 167

Text #8

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1778. Min Act: -0.1700

Data Index: 4852851 (Open Web Text)

Max Activating Token Index: 833

Text #9

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1690. Min Act: -0.1700

Data Index: 2141491 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1778. Min Act: -0.1700

Data Index: 7626385 (Open Web Text)

Max Activating Token Index: 819

Text #11

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1565. Min Act: -0.1700

Data Index: 3657685 (Open Web Text)

Max Activating Token Index: 762

Text #12

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1608. Min Act: -0.1700

Data Index: 7298466 (Open Web Text)

Max Activating Token Index: 713

Text #13

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1653. Min Act: -0.1700

Data Index: 3838648 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1623. Min Act: -0.1700

Data Index: 173324 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1561. Min Act: -0.1700

Data Index: 4657243 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1584. Min Act: -0.1700

Data Index: 1572788 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1500. Min Act: -0.1700

Data Index: 2811455 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1693. Min Act: -0.1700

Data Index: 3122544 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 3.2692. Min Range: -3.2692

Max Act: 3.1537. Min Act: -0.1700

Data Index: 2494032 (Open Web Text)

Max Activating Token Index: 732