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

Dataset: Open Web Text

Neuron 122 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: 4.1794. Min Range: -4.1794

Max Act: 4.1794. Min Act: -0.1700

Data Index: 5177414 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 4.1794. Min Range: -4.1794

Max Act: 4.1097. Min Act: -0.1700

Data Index: 2637808 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.1794. Min Range: -4.1794

Max Act: 4.0219. Min Act: -0.1700

Data Index: 7824012 (Open Web Text)

Max Activating Token Index: 1006

Text #3

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9698. Min Act: -0.1700

Data Index: 6043385 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9656. Min Act: -0.1700

Data Index: 7523769 (Open Web Text)

Max Activating Token Index: 944

Text #5

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9563. Min Act: -0.1700

Data Index: 7652123 (Open Web Text)

Max Activating Token Index: 877

Text #6

Max Range: 4.1794. Min Range: -4.1794

Max Act: 4.0224. Min Act: -0.1700

Data Index: 1356306 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 4.1794. Min Range: -4.1794

Max Act: 4.0012. Min Act: -0.1700

Data Index: 6771897 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9756. Min Act: -0.1700

Data Index: 5297059 (Open Web Text)

Max Activating Token Index: 499

Text #9

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9767. Min Act: -0.1700

Data Index: 7101273 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9611. Min Act: -0.1700

Data Index: 3871806 (Open Web Text)

Max Activating Token Index: 652

Text #11

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9705. Min Act: -0.1700

Data Index: 4884833 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 4.1794. Min Range: -4.1794

Max Act: 4.0079. Min Act: -0.1700

Data Index: 4687191 (Open Web Text)

Max Activating Token Index: 377

Text #13

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9393. Min Act: -0.1700

Data Index: 4299269 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9363. Min Act: -0.1700

Data Index: 1256699 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9702. Min Act: -0.1700

Data Index: 3161856 (Open Web Text)

Max Activating Token Index: 495

Text #16

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9125. Min Act: -0.1700

Data Index: 5058546 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9366. Min Act: -0.1700

Data Index: 6067155 (Open Web Text)

Max Activating Token Index: 622

Text #18

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9487. Min Act: -0.1700

Data Index: 6356193 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 4.1794. Min Range: -4.1794

Max Act: 3.9081. Min Act: -0.1700

Data Index: 2964648 (Open Web Text)

Max Activating Token Index: 905