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

Dataset: Open Web Text

Neuron 1654 in Layer 4

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: 4.7016. Min Range: -4.7016

Max Act: 4.6750. Min Act: -0.1700

Data Index: 6951671 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.6699. Min Act: -0.1700

Data Index: 2189 (Open Web Text)

Max Activating Token Index: 344

Text #2

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.7016. Min Act: -0.1700

Data Index: 5709414 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.5478. Min Act: -0.1700

Data Index: 6944018 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4977. Min Act: -0.1700

Data Index: 5821100 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4921. Min Act: -0.1700

Data Index: 3537370 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4699. Min Act: -0.1700

Data Index: 1521567 (Open Web Text)

Max Activating Token Index: 527

Text #7

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4098. Min Act: -0.1700

Data Index: 1599791 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4640. Min Act: -0.1700

Data Index: 6106133 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4218. Min Act: -0.1700

Data Index: 4583229 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4051. Min Act: -0.1700

Data Index: 6286272 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4145. Min Act: -0.1700

Data Index: 3009626 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4010. Min Act: -0.1700

Data Index: 370217 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.3789. Min Act: -0.1700

Data Index: 3840783 (Open Web Text)

Max Activating Token Index: 432

Text #14

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.4029. Min Act: -0.1700

Data Index: 868493 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.3785. Min Act: -0.1700

Data Index: 5943796 (Open Web Text)

Max Activating Token Index: 280

Text #16

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.3357. Min Act: -0.1700

Data Index: 4278443 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.3456. Min Act: -0.1700

Data Index: 2575697 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.3608. Min Act: -0.1700

Data Index: 367142 (Open Web Text)

Max Activating Token Index: 517

Text #19

Max Range: 4.7016. Min Range: -4.7016

Max Act: 4.3669. Min Act: -0.1700

Data Index: 6222357 (Open Web Text)

Max Activating Token Index: 842