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

Dataset: Open Web Text

Neuron 2609 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: 3.1698. Min Range: -3.1698

Max Act: 3.1698. Min Act: -0.1700

Data Index: 7955062 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.1503. Min Act: -0.1700

Data Index: 4751536 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0855. Min Act: -0.1700

Data Index: 6040064 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0795. Min Act: -0.1700

Data Index: 5853627 (Open Web Text)

Max Activating Token Index: 651

Text #4

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0886. Min Act: -0.1700

Data Index: 2187137 (Open Web Text)

Max Activating Token Index: 578

Text #5

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0605. Min Act: -0.1700

Data Index: 16679 (Open Web Text)

Max Activating Token Index: 768

Text #6

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0390. Min Act: -0.1700

Data Index: 652375 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0405. Min Act: -0.1700

Data Index: 670100 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0467. Min Act: -0.1700

Data Index: 1353390 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0460. Min Act: -0.1700

Data Index: 5617555 (Open Web Text)

Max Activating Token Index: 859

Text #10

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0270. Min Act: -0.1700

Data Index: 2068093 (Open Web Text)

Max Activating Token Index: 766

Text #11

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0069. Min Act: -0.1700

Data Index: 2844788 (Open Web Text)

Max Activating Token Index: 460

Text #12

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0321. Min Act: -0.1700

Data Index: 6614791 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0103. Min Act: -0.1700

Data Index: 5299002 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0212. Min Act: -0.1700

Data Index: 4661812 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0011. Min Act: -0.1700

Data Index: 5628562 (Open Web Text)

Max Activating Token Index: 510

Text #16

Max Range: 3.1698. Min Range: -3.1698

Max Act: 3.0093. Min Act: -0.1700

Data Index: 1023653 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 3.1698. Min Range: -3.1698

Max Act: 2.9918. Min Act: -0.1700

Data Index: 4357770 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 3.1698. Min Range: -3.1698

Max Act: 2.9903. Min Act: -0.1700

Data Index: 3707624 (Open Web Text)

Max Activating Token Index: 376

Text #19

Max Range: 3.1698. Min Range: -3.1698

Max Act: 2.9850. Min Act: -0.1700

Data Index: 2570129 (Open Web Text)

Max Activating Token Index: 466