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

Dataset: Open Web Text

Neuron 1037 in Layer 5

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: 3.9591. Min Range: -3.9591

Max Act: 3.9591. Min Act: -0.1700

Data Index: 2459670 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7563. Min Act: -0.1700

Data Index: 8558347 (Open Web Text)

Max Activating Token Index: 973

Text #2

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7119. Min Act: -0.1700

Data Index: 3564870 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7102. Min Act: -0.1700

Data Index: 4632838 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7193. Min Act: -0.1700

Data Index: 5488457 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7015. Min Act: -0.1700

Data Index: 491500 (Open Web Text)

Max Activating Token Index: 168

Text #6

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7126. Min Act: -0.1700

Data Index: 6494243 (Open Web Text)

Max Activating Token Index: 562

Text #7

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.7215. Min Act: -0.1700

Data Index: 5595847 (Open Web Text)

Max Activating Token Index: 660

Text #8

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6835. Min Act: -0.1700

Data Index: 6295988 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6505. Min Act: -0.1700

Data Index: 4942690 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6301. Min Act: -0.1700

Data Index: 7120093 (Open Web Text)

Max Activating Token Index: 848

Text #11

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6295. Min Act: -0.1700

Data Index: 4413855 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6260. Min Act: -0.1700

Data Index: 3543848 (Open Web Text)

Max Activating Token Index: 952

Text #13

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6039. Min Act: -0.1700

Data Index: 7169294 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6174. Min Act: -0.1700

Data Index: 485289 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.5836. Min Act: -0.1700

Data Index: 6315891 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.6065. Min Act: -0.1700

Data Index: 6965490 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.5731. Min Act: -0.1700

Data Index: 4425343 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.5885. Min Act: -0.1700

Data Index: 6999018 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 3.9591. Min Range: -3.9591

Max Act: 3.5864. Min Act: -0.1700

Data Index: 1273179 (Open Web Text)

Max Activating Token Index: 698