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

Dataset: Open Web Text

Neuron 2471 in Layer 6

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: 3.2832. Min Range: -3.2832

Max Act: 3.2832. Min Act: -0.1700

Data Index: 1969395 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.2426. Min Act: -0.1700

Data Index: 5523427 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1981. Min Act: -0.1700

Data Index: 2161189 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1786. Min Act: -0.1700

Data Index: 6753356 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1680. Min Act: -0.1700

Data Index: 4471994 (Open Web Text)

Max Activating Token Index: 296

Text #5

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1696. Min Act: -0.1700

Data Index: 1576050 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1420. Min Act: -0.1700

Data Index: 4016160 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1452. Min Act: -0.1700

Data Index: 3930466 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1168. Min Act: -0.1700

Data Index: 3482000 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1137. Min Act: -0.1700

Data Index: 5734901 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1179. Min Act: -0.1700

Data Index: 1246714 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1082. Min Act: -0.1700

Data Index: 5263384 (Open Web Text)

Max Activating Token Index: 983

Text #12

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0813. Min Act: -0.1700

Data Index: 885870 (Open Web Text)

Max Activating Token Index: 579

Text #13

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1122. Min Act: -0.1700

Data Index: 5918866 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0946. Min Act: -0.1700

Data Index: 4867623 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.1036. Min Act: -0.1700

Data Index: 4259560 (Open Web Text)

Max Activating Token Index: 142

Text #16

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0927. Min Act: -0.1700

Data Index: 883 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0807. Min Act: -0.1700

Data Index: 7753418 (Open Web Text)

Max Activating Token Index: 834

Text #18

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0657. Min Act: -0.1700

Data Index: 5395778 (Open Web Text)

Max Activating Token Index: 273

Text #19

Max Range: 3.2832. Min Range: -3.2832

Max Act: 3.0795. Min Act: -0.1700

Data Index: 6800278 (Open Web Text)

Max Activating Token Index: 491