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

Dataset: Open Web Text

Neuron 1862 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: 3.7015. Min Range: -3.7015

Max Act: 3.6800. Min Act: -0.1700

Data Index: 7160130 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.7015. Min Act: -0.1700

Data Index: 6475198 (Open Web Text)

Max Activating Token Index: 458

Text #2

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6679. Min Act: -0.1700

Data Index: 5633831 (Open Web Text)

Max Activating Token Index: 678

Text #3

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6729. Min Act: -0.1700

Data Index: 1966061 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6886. Min Act: -0.1700

Data Index: 1798451 (Open Web Text)

Max Activating Token Index: 952

Text #5

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6950. Min Act: -0.1700

Data Index: 208545 (Open Web Text)

Max Activating Token Index: 953

Text #6

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6554. Min Act: -0.1700

Data Index: 7492753 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6495. Min Act: -0.1700

Data Index: 512831 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6447. Min Act: -0.1700

Data Index: 5036134 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6739. Min Act: -0.1700

Data Index: 4089597 (Open Web Text)

Max Activating Token Index: 765

Text #10

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6646. Min Act: -0.1700

Data Index: 845552 (Open Web Text)

Max Activating Token Index: 828

Text #11

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6398. Min Act: -0.1700

Data Index: 3724874 (Open Web Text)

Max Activating Token Index: 379

Text #12

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6541. Min Act: -0.1700

Data Index: 8177499 (Open Web Text)

Max Activating Token Index: 415

Text #13

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6148. Min Act: -0.1700

Data Index: 4494541 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6038. Min Act: -0.1700

Data Index: 5470614 (Open Web Text)

Max Activating Token Index: 422

Text #15

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6067. Min Act: -0.1700

Data Index: 3610917 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6077. Min Act: -0.1700

Data Index: 2224359 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6517. Min Act: -0.1700

Data Index: 6402571 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.5772. Min Act: -0.1700

Data Index: 6463197 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 3.7015. Min Range: -3.7015

Max Act: 3.6171. Min Act: -0.1700

Data Index: 1973051 (Open Web Text)

Max Activating Token Index: 578