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

Dataset: Open Web Text

Neuron 164 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: 3.5836. Min Range: -3.5836

Max Act: 3.5836. Min Act: -0.1700

Data Index: 6680929 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1243650 (Open Web Text)

Max Activating Token Index: 946

Text #2

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.5286. Min Act: -0.1700

Data Index: 7434639 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4771. Min Act: -0.1700

Data Index: 7670964 (Open Web Text)

Max Activating Token Index: 865

Text #4

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.5064. Min Act: -0.1700

Data Index: 840613 (Open Web Text)

Max Activating Token Index: 902

Text #5

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4706. Min Act: -0.1700

Data Index: 4125155 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4776. Min Act: -0.1700

Data Index: 6034415 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.5164. Min Act: -0.1700

Data Index: 8142130 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4528. Min Act: -0.1700

Data Index: 4581003 (Open Web Text)

Max Activating Token Index: 330

Text #9

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4810. Min Act: -0.1700

Data Index: 5535126 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4496. Min Act: -0.1700

Data Index: 6721286 (Open Web Text)

Max Activating Token Index: 1002

Text #11

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4758. Min Act: -0.1700

Data Index: 3979880 (Open Web Text)

Max Activating Token Index: 737

Text #12

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4452. Min Act: -0.1700

Data Index: 8305524 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4278. Min Act: -0.1700

Data Index: 5703456 (Open Web Text)

Max Activating Token Index: 295

Text #14

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4364. Min Act: -0.1700

Data Index: 2438980 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4218. Min Act: -0.1700

Data Index: 8317235 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4191. Min Act: -0.1700

Data Index: 7876145 (Open Web Text)

Max Activating Token Index: 605

Text #17

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.4052. Min Act: -0.1700

Data Index: 6130833 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.3826. Min Act: -0.1700

Data Index: 4007185 (Open Web Text)

Max Activating Token Index: 989

Text #19

Max Range: 3.5836. Min Range: -3.5836

Max Act: 3.3852. Min Act: -0.1700

Data Index: 8077484 (Open Web Text)

Max Activating Token Index: 206