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

Dataset: Open Web Text

Neuron 2472 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: 4.0757. Min Range: -4.0757

Max Act: 4.0625. Min Act: -0.1700

Data Index: 152612 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0632. Min Act: -0.1700

Data Index: 3921657 (Open Web Text)

Max Activating Token Index: 712

Text #2

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0757. Min Act: -0.1700

Data Index: 3710421 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0563. Min Act: -0.1700

Data Index: 5201265 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0455. Min Act: -0.1700

Data Index: 8605862 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0148. Min Act: -0.1700

Data Index: 8327498 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0072. Min Act: -0.1700

Data Index: 6929414 (Open Web Text)

Max Activating Token Index: 724

Text #7

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0111. Min Act: -0.1700

Data Index: 2880791 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9972. Min Act: -0.1700

Data Index: 5755564 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 4.0757. Min Range: -4.0757

Max Act: 4.0100. Min Act: -0.1700

Data Index: 5755563 (Open Web Text)

Max Activating Token Index: 724

Text #10

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9991. Min Act: -0.1700

Data Index: 1686790 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9753. Min Act: -0.1700

Data Index: 7691681 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9664. Min Act: -0.1700

Data Index: 480276 (Open Web Text)

Max Activating Token Index: 905

Text #13

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9877. Min Act: -0.1700

Data Index: 7285386 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9637. Min Act: -0.1700

Data Index: 792224 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9767. Min Act: -0.1700

Data Index: 7412009 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9635. Min Act: -0.1700

Data Index: 4508258 (Open Web Text)

Max Activating Token Index: 353

Text #17

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9519. Min Act: -0.1700

Data Index: 1886127 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9500. Min Act: -0.1700

Data Index: 341123 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 4.0757. Min Range: -4.0757

Max Act: 3.9683. Min Act: -0.1700

Data Index: 3023705 (Open Web Text)

Max Activating Token Index: 432