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

Dataset: Open Web Text

Neuron 712 in Layer 3

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: 4.1313. Min Range: -4.1313

Max Act: 4.1313. Min Act: -0.1700

Data Index: 5701968 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0652. Min Act: -0.1700

Data Index: 4736375 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0507. Min Act: -0.1700

Data Index: 7446656 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 4.1313. Min Range: -4.1313

Max Act: 4.0313. Min Act: -0.1700

Data Index: 1133693 (Open Web Text)

Max Activating Token Index: 178

Text #4

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9964. Min Act: -0.1700

Data Index: 6772559 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9794. Min Act: -0.1700

Data Index: 6186460 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9748. Min Act: -0.1700

Data Index: 1477186 (Open Web Text)

Max Activating Token Index: 830

Text #7

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9518. Min Act: -0.1700

Data Index: 4916541 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8833. Min Act: -0.1700

Data Index: 5446796 (Open Web Text)

Max Activating Token Index: 851

Text #9

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9137. Min Act: -0.1700

Data Index: 7420220 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9230. Min Act: -0.1700

Data Index: 4965929 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9141. Min Act: -0.1700

Data Index: 5230641 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8885. Min Act: -0.1700

Data Index: 5778038 (Open Web Text)

Max Activating Token Index: 662

Text #13

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.9305. Min Act: -0.1700

Data Index: 1178957 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8912. Min Act: -0.1700

Data Index: 1390212 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8590. Min Act: -0.1700

Data Index: 2014211 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8428. Min Act: -0.1700

Data Index: 1471496 (Open Web Text)

Max Activating Token Index: 777

Text #17

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8626. Min Act: -0.1700

Data Index: 3563947 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8615. Min Act: -0.1700

Data Index: 5736336 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 4.1313. Min Range: -4.1313

Max Act: 3.8637. Min Act: -0.1700

Data Index: 3346191 (Open Web Text)

Max Activating Token Index: 615