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

Dataset: Open Web Text

Neuron 1959 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: 3.9797. Min Range: -3.9797

Max Act: 3.9797. Min Act: -0.1700

Data Index: 3989822 (Open Web Text)

Max Activating Token Index: 486

Text #1

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.8677. Min Act: -0.1700

Data Index: 1359400 (Open Web Text)

Max Activating Token Index: 829

Text #2

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.7521. Min Act: -0.1700

Data Index: 840560 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.7155. Min Act: -0.1700

Data Index: 6216772 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.7282. Min Act: -0.1700

Data Index: 537536 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.7146. Min Act: -0.1700

Data Index: 5830533 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.6386. Min Act: -0.1700

Data Index: 6155918 (Open Web Text)

Max Activating Token Index: 971

Text #7

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.6805. Min Act: -0.1700

Data Index: 8623907 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5417. Min Act: -0.1700

Data Index: 6353274 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5905. Min Act: -0.1700

Data Index: 4938422 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5648. Min Act: -0.1700

Data Index: 5620136 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5923. Min Act: -0.1700

Data Index: 607796 (Open Web Text)

Max Activating Token Index: 1012

Text #12

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5843. Min Act: -0.1700

Data Index: 1250843 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5857. Min Act: -0.1700

Data Index: 2030776 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5603. Min Act: -0.1700

Data Index: 8456419 (Open Web Text)

Max Activating Token Index: 235

Text #15

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5799. Min Act: -0.1700

Data Index: 722439 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5526. Min Act: -0.1700

Data Index: 1690936 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5467. Min Act: -0.1700

Data Index: 738926 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5009. Min Act: -0.1700

Data Index: 4559909 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 3.9797. Min Range: -3.9797

Max Act: 3.5112. Min Act: -0.1700

Data Index: 5342401 (Open Web Text)

Max Activating Token Index: 532