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

Dataset: Open Web Text

Neuron 2 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: 4.1709. Min Range: -4.1709

Max Act: 4.1709. Min Act: -0.1700

Data Index: 7306026 (Open Web Text)

Max Activating Token Index: 163

Text #1

Max Range: 4.1709. Min Range: -4.1709

Max Act: 4.0413. Min Act: -0.1700

Data Index: 6673334 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9506. Min Act: -0.1700

Data Index: 3003178 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9433. Min Act: -0.1700

Data Index: 4228359 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9409. Min Act: -0.1700

Data Index: 4998854 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9226. Min Act: -0.1700

Data Index: 5829257 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9091. Min Act: -0.1700

Data Index: 8667359 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9290. Min Act: -0.1700

Data Index: 3714986 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.9178. Min Act: -0.1700

Data Index: 2017373 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8927. Min Act: -0.1700

Data Index: 4548796 (Open Web Text)

Max Activating Token Index: 725

Text #10

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8799. Min Act: -0.1700

Data Index: 8416264 (Open Web Text)

Max Activating Token Index: 851

Text #11

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8483. Min Act: -0.1700

Data Index: 540883 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8602. Min Act: -0.1700

Data Index: 6720320 (Open Web Text)

Max Activating Token Index: 203

Text #13

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8712. Min Act: -0.1700

Data Index: 8304447 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8846. Min Act: -0.1700

Data Index: 3848930 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8818. Min Act: -0.1700

Data Index: 4412410 (Open Web Text)

Max Activating Token Index: 744

Text #16

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8736. Min Act: -0.1700

Data Index: 2655057 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8720. Min Act: -0.1700

Data Index: 7425439 (Open Web Text)

Max Activating Token Index: 953

Text #18

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8677. Min Act: -0.1700

Data Index: 2448363 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 4.1709. Min Range: -4.1709

Max Act: 3.8560. Min Act: -0.1700

Data Index: 4972927 (Open Web Text)

Max Activating Token Index: 525