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

Dataset: Open Web Text

Neuron 602 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: 3.2119. Min Range: -3.2119

Max Act: 3.2119. Min Act: -0.1700

Data Index: 6509671 (Open Web Text)

Max Activating Token Index: 835

Text #1

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.9198. Min Act: -0.1700

Data Index: 6153888 (Open Web Text)

Max Activating Token Index: 905

Text #2

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8982. Min Act: -0.1700

Data Index: 7828849 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.9062. Min Act: -0.1700

Data Index: 2309516 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8845. Min Act: -0.1700

Data Index: 2103695 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8751. Min Act: -0.1700

Data Index: 7088257 (Open Web Text)

Max Activating Token Index: 522

Text #6

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8891. Min Act: -0.1700

Data Index: 1822803 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8732. Min Act: -0.1700

Data Index: 5278806 (Open Web Text)

Max Activating Token Index: 885

Text #8

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8668. Min Act: -0.1700

Data Index: 8555328 (Open Web Text)

Max Activating Token Index: 416

Text #9

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8339. Min Act: -0.1700

Data Index: 5416372 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8232. Min Act: -0.1700

Data Index: 5278805 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8285. Min Act: -0.1700

Data Index: 645153 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8199. Min Act: -0.1700

Data Index: 5278807 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8385. Min Act: -0.1700

Data Index: 6779293 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.7939. Min Act: -0.1700

Data Index: 1364838 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8106. Min Act: -0.1700

Data Index: 4923892 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.8004. Min Act: -0.1700

Data Index: 1253626 (Open Web Text)

Max Activating Token Index: 879

Text #17

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.7667. Min Act: -0.1700

Data Index: 344411 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.7913. Min Act: -0.1700

Data Index: 7521969 (Open Web Text)

Max Activating Token Index: 748

Text #19

Max Range: 3.2119. Min Range: -3.2119

Max Act: 2.7568. Min Act: -0.1700

Data Index: 8509693 (Open Web Text)

Max Activating Token Index: 1014