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

Dataset: Open Web Text

Neuron 694 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: 3.2807. Min Range: -3.2807

Max Act: 3.2807. Min Act: -0.1700

Data Index: 3817702 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.2401. Min Act: -0.1700

Data Index: 2916384 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1713. Min Act: -0.1700

Data Index: 4883006 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1841. Min Act: -0.1700

Data Index: 7521033 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1831. Min Act: -0.1700

Data Index: 2498465 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1697. Min Act: -0.1700

Data Index: 6173881 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1340. Min Act: -0.1700

Data Index: 137303 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0851. Min Act: -0.1700

Data Index: 8385161 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1126. Min Act: -0.1700

Data Index: 4174913 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0878. Min Act: -0.1700

Data Index: 7454551 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0688. Min Act: -0.1700

Data Index: 8300979 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0831. Min Act: -0.1700

Data Index: 2808739 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0932. Min Act: -0.1700

Data Index: 5432922 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0838. Min Act: -0.1700

Data Index: 3393883 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0639. Min Act: -0.1700

Data Index: 8251646 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0660. Min Act: -0.1700

Data Index: 2621475 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0513. Min Act: -0.1700

Data Index: 907727 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0588. Min Act: -0.1700

Data Index: 7461038 (Open Web Text)

Max Activating Token Index: 982

Text #18

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0698. Min Act: -0.1700

Data Index: 4393179 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0389. Min Act: -0.1700

Data Index: 5981146 (Open Web Text)

Max Activating Token Index: 764