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

Dataset: Open Web Text

Neuron 874 in Layer 6

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: 3.9779. Min Range: -3.9779

Max Act: 3.9779. Min Act: -0.1700

Data Index: 2976475 (Open Web Text)

Max Activating Token Index: 657

Text #1

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.9140. Min Act: -0.1700

Data Index: 3577171 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.9190. Min Act: -0.1700

Data Index: 1671903 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.8658. Min Act: -0.1700

Data Index: 1307975 (Open Web Text)

Max Activating Token Index: 419

Text #4

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7900. Min Act: -0.1700

Data Index: 6967543 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.8007. Min Act: -0.1700

Data Index: 7786552 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7749. Min Act: -0.1700

Data Index: 4527107 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7927. Min Act: -0.1700

Data Index: 3145786 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7669. Min Act: -0.1700

Data Index: 615562 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7685. Min Act: -0.1700

Data Index: 594009 (Open Web Text)

Max Activating Token Index: 425

Text #10

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7852. Min Act: -0.1700

Data Index: 100919 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7808. Min Act: -0.1700

Data Index: 5897127 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7665. Min Act: -0.1700

Data Index: 2924684 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7847. Min Act: -0.1700

Data Index: 5820820 (Open Web Text)

Max Activating Token Index: 895

Text #14

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7582. Min Act: -0.1700

Data Index: 4697242 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7889. Min Act: -0.1700

Data Index: 293674 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7591. Min Act: -0.1700

Data Index: 4462815 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7646. Min Act: -0.1700

Data Index: 1991016 (Open Web Text)

Max Activating Token Index: 411

Text #18

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7445. Min Act: -0.1700

Data Index: 4064072 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 3.9779. Min Range: -3.9779

Max Act: 3.7479. Min Act: -0.1700

Data Index: 2140038 (Open Web Text)

Max Activating Token Index: 849