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

Dataset: Open Web Text

Neuron 1147 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: 3.1718. Min Range: -3.1718

Max Act: 3.1718. Min Act: -0.1700

Data Index: 6176115 (Open Web Text)

Max Activating Token Index: 333

Text #1

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.0848. Min Act: -0.1700

Data Index: 2077722 (Open Web Text)

Max Activating Token Index: 641

Text #2

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.1046. Min Act: -0.1700

Data Index: 4599740 (Open Web Text)

Max Activating Token Index: 539

Text #3

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.0399. Min Act: -0.1700

Data Index: 928423 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.0490. Min Act: -0.1700

Data Index: 7854283 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.0206. Min Act: -0.1700

Data Index: 6863410 (Open Web Text)

Max Activating Token Index: 187

Text #6

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.0296. Min Act: -0.1700

Data Index: 3466793 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 3.1718. Min Range: -3.1718

Max Act: 3.0181. Min Act: -0.1700

Data Index: 4905597 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9867. Min Act: -0.1700

Data Index: 6850855 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9538. Min Act: -0.1700

Data Index: 7757373 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9562. Min Act: -0.1700

Data Index: 6017971 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9770. Min Act: -0.1700

Data Index: 7265349 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9558. Min Act: -0.1700

Data Index: 3535368 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9847. Min Act: -0.1700

Data Index: 2624055 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9486. Min Act: -0.1700

Data Index: 3085939 (Open Web Text)

Max Activating Token Index: 478

Text #15

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9586. Min Act: -0.1700

Data Index: 7627856 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9477. Min Act: -0.1700

Data Index: 2967332 (Open Web Text)

Max Activating Token Index: 959

Text #17

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9443. Min Act: -0.1700

Data Index: 4930089 (Open Web Text)

Max Activating Token Index: 316

Text #18

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9475. Min Act: -0.1700

Data Index: 3091041 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.1718. Min Range: -3.1718

Max Act: 2.9610. Min Act: -0.1700

Data Index: 7225631 (Open Web Text)

Max Activating Token Index: 711