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

Dataset: Open Web Text

Neuron 10 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: 1.5952. Min Range: -1.5952

Max Act: 1.5952. Min Act: -0.1692

Data Index: 5451570 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4833. Min Act: -0.1690

Data Index: 5451557 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4884. Min Act: -0.1697

Data Index: 5451571 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4802. Min Act: -0.1661

Data Index: 4488797 (Open Web Text)

Max Activating Token Index: 444

Text #4

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4690. Min Act: -0.1700

Data Index: 4488802 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4753. Min Act: -0.1700

Data Index: 8502050 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4694. Min Act: -0.1603

Data Index: 5451565 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4678. Min Act: -0.1690

Data Index: 8502048 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4673. Min Act: -0.1579

Data Index: 5451561 (Open Web Text)

Max Activating Token Index: 241

Text #9

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4644. Min Act: -0.1690

Data Index: 4488801 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4779. Min Act: -0.1659

Data Index: 8502019 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4678. Min Act: -0.1635

Data Index: 5451562 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4615. Min Act: -0.1692

Data Index: 5451566 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4626. Min Act: -0.1695

Data Index: 4488796 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4599. Min Act: -0.1695

Data Index: 5451556 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4633. Min Act: -0.1562

Data Index: 8502049 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4491. Min Act: -0.1626

Data Index: 4488800 (Open Web Text)

Max Activating Token Index: 453

Text #17

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4453. Min Act: -0.1692

Data Index: 5451558 (Open Web Text)

Max Activating Token Index: 174

Text #18

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4341. Min Act: -0.1690

Data Index: 15439 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4372. Min Act: -0.1580

Data Index: 5451569 (Open Web Text)

Max Activating Token Index: 716