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

Dataset: Open Web Text

Neuron 2899 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: 1.6196. Min Range: -1.6196

Max Act: 1.6196. Min Act: -0.1700

Data Index: 7933301 (Open Web Text)

Max Activating Token Index: 354

Text #1

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5890. Min Act: -0.1700

Data Index: 1429172 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5902. Min Act: -0.1700

Data Index: 301745 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5774. Min Act: -0.1700

Data Index: 8188779 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5833. Min Act: -0.1700

Data Index: 8636834 (Open Web Text)

Max Activating Token Index: 354

Text #5

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5836. Min Act: -0.1698

Data Index: 2049806 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5781. Min Act: -0.1700

Data Index: 5470254 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5794. Min Act: -0.1700

Data Index: 7096761 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5735. Min Act: -0.1700

Data Index: 7821126 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5662. Min Act: -0.1700

Data Index: 63941 (Open Web Text)

Max Activating Token Index: 534

Text #10

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5655. Min Act: -0.1700

Data Index: 167946 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5704. Min Act: -0.1700

Data Index: 4397926 (Open Web Text)

Max Activating Token Index: 629

Text #12

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5697. Min Act: -0.1700

Data Index: 7227836 (Open Web Text)

Max Activating Token Index: 350

Text #13

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5727. Min Act: -0.1700

Data Index: 7760942 (Open Web Text)

Max Activating Token Index: 411

Text #14

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5718. Min Act: -0.1700

Data Index: 1123080 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5690. Min Act: -0.1700

Data Index: 7719186 (Open Web Text)

Max Activating Token Index: 271

Text #16

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5757. Min Act: -0.1700

Data Index: 2759127 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5611. Min Act: -0.1700

Data Index: 6522123 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5651. Min Act: -0.1700

Data Index: 5793492 (Open Web Text)

Max Activating Token Index: 328

Text #19

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5717. Min Act: -0.1700

Data Index: 7536116 (Open Web Text)

Max Activating Token Index: 260