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

Dataset: Open Web Text

Neuron 39 in Layer 5

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: 4.0796. Min Range: -4.0796

Max Act: 4.0796. Min Act: -0.1700

Data Index: 7905660 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 4.0796. Min Range: -4.0796

Max Act: 4.0272. Min Act: -0.1700

Data Index: 2653834 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.8832. Min Act: -0.1700

Data Index: 415060 (Open Web Text)

Max Activating Token Index: 384

Text #3

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.8391. Min Act: -0.1700

Data Index: 2480575 (Open Web Text)

Max Activating Token Index: 818

Text #4

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.8164. Min Act: -0.1700

Data Index: 3276643 (Open Web Text)

Max Activating Token Index: 764

Text #5

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7859. Min Act: -0.1700

Data Index: 4646006 (Open Web Text)

Max Activating Token Index: 374

Text #6

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.8057. Min Act: -0.1700

Data Index: 376571 (Open Web Text)

Max Activating Token Index: 936

Text #7

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7875. Min Act: -0.1700

Data Index: 594338 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7853. Min Act: -0.1700

Data Index: 8325385 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.8011. Min Act: -0.1700

Data Index: 1606940 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7791. Min Act: -0.1700

Data Index: 6551337 (Open Web Text)

Max Activating Token Index: 554

Text #11

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7707. Min Act: -0.1700

Data Index: 31117 (Open Web Text)

Max Activating Token Index: 917

Text #12

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.8171. Min Act: -0.1700

Data Index: 2127361 (Open Web Text)

Max Activating Token Index: 743

Text #13

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7873. Min Act: -0.1700

Data Index: 3508305 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7766. Min Act: -0.1700

Data Index: 5945631 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7601. Min Act: -0.1700

Data Index: 7437749 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7776. Min Act: -0.1700

Data Index: 4849554 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7504. Min Act: -0.1700

Data Index: 5337251 (Open Web Text)

Max Activating Token Index: 919

Text #18

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7798. Min Act: -0.1700

Data Index: 433418 (Open Web Text)

Max Activating Token Index: 220

Text #19

Max Range: 4.0796. Min Range: -4.0796

Max Act: 3.7746. Min Act: -0.1700

Data Index: 1410648 (Open Web Text)

Max Activating Token Index: 337