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

Dataset: Open Web Text

Neuron 2587 in Layer 2

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: 4.3077. Min Range: -4.3077

Max Act: 4.3077. Min Act: -0.1700

Data Index: 4401857 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1745. Min Act: -0.1700

Data Index: 6212834 (Open Web Text)

Max Activating Token Index: 654

Text #2

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1839. Min Act: -0.1700

Data Index: 6921859 (Open Web Text)

Max Activating Token Index: 999

Text #3

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1824. Min Act: -0.1700

Data Index: 1753623 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1424. Min Act: -0.1700

Data Index: 3733377 (Open Web Text)

Max Activating Token Index: 307

Text #5

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1526. Min Act: -0.1700

Data Index: 4297700 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1377. Min Act: -0.1700

Data Index: 1096197 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1212. Min Act: -0.1700

Data Index: 1866311 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1732. Min Act: -0.1700

Data Index: 8092300 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1463. Min Act: -0.1700

Data Index: 240193 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1704. Min Act: -0.1700

Data Index: 6258129 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1064. Min Act: -0.1700

Data Index: 3396454 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1115. Min Act: -0.1700

Data Index: 3063537 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1178. Min Act: -0.1700

Data Index: 6702233 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1165. Min Act: -0.1700

Data Index: 1703312 (Open Web Text)

Max Activating Token Index: 661

Text #15

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1109. Min Act: -0.1700

Data Index: 7167312 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.0975. Min Act: -0.1700

Data Index: 4423002 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1016. Min Act: -0.1700

Data Index: 4427535 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1353. Min Act: -0.1700

Data Index: 4758015 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.3077. Min Range: -4.3077

Max Act: 4.1323. Min Act: -0.1700

Data Index: 7502019 (Open Web Text)

Max Activating Token Index: 406