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

Dataset: Open Web Text

Neuron 262 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: 3.1731. Min Range: -3.1731

Max Act: 3.1675. Min Act: -0.1700

Data Index: 5622903 (Open Web Text)

Max Activating Token Index: 714

Text #1

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1731. Min Act: -0.1700

Data Index: 867727 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1387. Min Act: -0.1700

Data Index: 5006563 (Open Web Text)

Max Activating Token Index: 815

Text #3

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1084. Min Act: -0.1700

Data Index: 5413259 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1044315 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1175. Min Act: -0.1700

Data Index: 3024236 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0971. Min Act: -0.1700

Data Index: 5703539 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0975. Min Act: -0.1700

Data Index: 8565431 (Open Web Text)

Max Activating Token Index: 868

Text #8

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1266. Min Act: -0.1700

Data Index: 6768905 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1120. Min Act: -0.1700

Data Index: 2090272 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0738. Min Act: -0.1700

Data Index: 7354918 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0668. Min Act: -0.1700

Data Index: 7066463 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1062. Min Act: -0.1700

Data Index: 2878303 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0945. Min Act: -0.1700

Data Index: 6156786 (Open Web Text)

Max Activating Token Index: 711

Text #14

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1035. Min Act: -0.1700

Data Index: 6099570 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0895. Min Act: -0.1700

Data Index: 7756841 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.1051. Min Act: -0.1700

Data Index: 6456231 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0529. Min Act: -0.1700

Data Index: 6099062 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0757. Min Act: -0.1700

Data Index: 7594480 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 3.1731. Min Range: -3.1731

Max Act: 3.0783. Min Act: -0.1700

Data Index: 2537726 (Open Web Text)

Max Activating Token Index: 368