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

Dataset: Open Web Text

Neuron 282 in Layer 0

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: 1.8121. Min Range: -1.8121

Max Act: 1.8121. Min Act: -0.1667

Data Index: 2860217 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7474. Min Act: -0.1634

Data Index: 2616257 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7373. Min Act: -0.1693

Data Index: 1914265 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7315. Min Act: -0.1638

Data Index: 1164397 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7247. Min Act: -0.1698

Data Index: 6991143 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7255. Min Act: -0.1700

Data Index: 333214 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7204. Min Act: -0.1488

Data Index: 6772078 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7187. Min Act: -0.1700

Data Index: 6863894 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7077. Min Act: -0.1697

Data Index: 4171351 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7070. Min Act: -0.1414

Data Index: 3518143 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7076. Min Act: -0.1654

Data Index: 1979783 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7015. Min Act: -0.1694

Data Index: 2958266 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7094. Min Act: -0.1628

Data Index: 4256116 (Open Web Text)

Max Activating Token Index: 652

Text #13

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6989. Min Act: -0.1646

Data Index: 5817061 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6965. Min Act: -0.1700

Data Index: 6689261 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6942. Min Act: -0.1693

Data Index: 93820 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6923. Min Act: -0.1645

Data Index: 620247 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6820. Min Act: -0.1545

Data Index: 656163 (Open Web Text)

Max Activating Token Index: 582

Text #18

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6828. Min Act: -0.1691

Data Index: 2166422 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6800. Min Act: -0.1658

Data Index: 2650533 (Open Web Text)

Max Activating Token Index: 5