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

Dataset: Open Web Text

Neuron 909 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: 1.6323. Min Range: -1.6323

Max Act: 1.6323. Min Act: -0.1698

Data Index: 2229208 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.5412. Min Act: -0.1700

Data Index: 2979993 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.5157. Min Act: -0.1700

Data Index: 483921 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.5124. Min Act: -0.1700

Data Index: 5241512 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.5029. Min Act: -0.1700

Data Index: 7405581 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.5108. Min Act: -0.1700

Data Index: 4487095 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4844. Min Act: -0.1700

Data Index: 4937582 (Open Web Text)

Max Activating Token Index: 193

Text #7

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4904. Min Act: -0.1700

Data Index: 6931762 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4828. Min Act: -0.1700

Data Index: 3047266 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4805. Min Act: -0.1700

Data Index: 1641549 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4779. Min Act: -0.1700

Data Index: 6195400 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4757. Min Act: -0.1700

Data Index: 4561930 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4718. Min Act: -0.1699

Data Index: 6176373 (Open Web Text)

Max Activating Token Index: 41

Text #13

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4805. Min Act: -0.1700

Data Index: 3151985 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4773. Min Act: -0.1700

Data Index: 1695693 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4763. Min Act: -0.1700

Data Index: 5867901 (Open Web Text)

Max Activating Token Index: 204

Text #16

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4720. Min Act: -0.1700

Data Index: 1493684 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4730. Min Act: -0.1700

Data Index: 8149677 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4836. Min Act: -0.1700

Data Index: 6382688 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4713. Min Act: -0.1700

Data Index: 3881829 (Open Web Text)

Max Activating Token Index: 168