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

Dataset: Open Web Text

Neuron 832 in Layer 1

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: 4.0794. Min Range: -4.0794

Max Act: 4.0794. Min Act: -0.1700

Data Index: 2350419 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 4.0794. Min Range: -4.0794

Max Act: 4.0755. Min Act: -0.1700

Data Index: 2043637 (Open Web Text)

Max Activating Token Index: 659

Text #2

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9887. Min Act: -0.1700

Data Index: 1914401 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 4.0794. Min Range: -4.0794

Max Act: 4.0149. Min Act: -0.1700

Data Index: 4310103 (Open Web Text)

Max Activating Token Index: 85

Text #4

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9939. Min Act: -0.1700

Data Index: 4205248 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 4.0794. Min Range: -4.0794

Max Act: 4.0038. Min Act: -0.1700

Data Index: 3334651 (Open Web Text)

Max Activating Token Index: 175

Text #6

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9661. Min Act: -0.1700

Data Index: 8543877 (Open Web Text)

Max Activating Token Index: 655

Text #7

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9834. Min Act: -0.1700

Data Index: 256347 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9783. Min Act: -0.1700

Data Index: 5005593 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9533. Min Act: -0.1700

Data Index: 4493758 (Open Web Text)

Max Activating Token Index: 154

Text #10

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9644. Min Act: -0.1700

Data Index: 4178080 (Open Web Text)

Max Activating Token Index: 119

Text #11

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9782. Min Act: -0.1700

Data Index: 8116525 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9654. Min Act: -0.1700

Data Index: 6122508 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9635. Min Act: -0.1700

Data Index: 3651922 (Open Web Text)

Max Activating Token Index: 744

Text #14

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9709. Min Act: -0.1700

Data Index: 3649436 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9711. Min Act: -0.1700

Data Index: 6043359 (Open Web Text)

Max Activating Token Index: 396

Text #16

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9505. Min Act: -0.1700

Data Index: 2498225 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9555. Min Act: -0.1700

Data Index: 4791606 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9146. Min Act: -0.1700

Data Index: 1878270 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 4.0794. Min Range: -4.0794

Max Act: 3.9275. Min Act: -0.1700

Data Index: 1878274 (Open Web Text)

Max Activating Token Index: 182