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

Dataset: Open Web Text

Neuron 1582 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: 2.8556. Min Range: -2.8556

Max Act: 2.8556. Min Act: -0.1700

Data Index: 6683030 (Open Web Text)

Max Activating Token Index: 726

Text #1

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7001. Min Act: -0.1700

Data Index: 185226 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.7014. Min Act: -0.1700

Data Index: 379120 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6382. Min Act: -0.1700

Data Index: 601762 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6647. Min Act: -0.1700

Data Index: 4854742 (Open Web Text)

Max Activating Token Index: 978

Text #5

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6299. Min Act: -0.1700

Data Index: 989861 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6378. Min Act: -0.1700

Data Index: 3273050 (Open Web Text)

Max Activating Token Index: 334

Text #7

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6184. Min Act: -0.1700

Data Index: 8496443 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6085. Min Act: -0.1700

Data Index: 215829 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6095. Min Act: -0.1700

Data Index: 3326630 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6070. Min Act: -0.1700

Data Index: 5814875 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6100. Min Act: -0.1700

Data Index: 6410151 (Open Web Text)

Max Activating Token Index: 1010

Text #12

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6080. Min Act: -0.1700

Data Index: 5129174 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6043. Min Act: -0.1700

Data Index: 2059311 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.6029. Min Act: -0.1700

Data Index: 5221396 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.5890. Min Act: -0.1700

Data Index: 2082123 (Open Web Text)

Max Activating Token Index: 625

Text #16

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.5929. Min Act: -0.1700

Data Index: 935000 (Open Web Text)

Max Activating Token Index: 740

Text #17

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.5924. Min Act: -0.1700

Data Index: 4781963 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.5899. Min Act: -0.1700

Data Index: 6699632 (Open Web Text)

Max Activating Token Index: 481

Text #19

Max Range: 2.8556. Min Range: -2.8556

Max Act: 2.5944. Min Act: -0.1700

Data Index: 7620173 (Open Web Text)

Max Activating Token Index: 284