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

Dataset: Open Web Text

Neuron 1000 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: 4.0172. Min Range: -4.0172

Max Act: 4.0013. Min Act: -0.1700

Data Index: 6521536 (Open Web Text)

Max Activating Token Index: 278

Text #1

Max Range: 4.0172. Min Range: -4.0172

Max Act: 4.0172. Min Act: -0.1700

Data Index: 8623266 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9531. Min Act: -0.1700

Data Index: 2030555 (Open Web Text)

Max Activating Token Index: 467

Text #3

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9354. Min Act: -0.1700

Data Index: 6821454 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9698. Min Act: -0.1700

Data Index: 2970641 (Open Web Text)

Max Activating Token Index: 777

Text #5

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9398. Min Act: -0.1700

Data Index: 7767143 (Open Web Text)

Max Activating Token Index: 942

Text #6

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9593. Min Act: -0.1700

Data Index: 3437603 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8928. Min Act: -0.1699

Data Index: 1704507 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9154. Min Act: -0.1700

Data Index: 7176421 (Open Web Text)

Max Activating Token Index: 410

Text #9

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8698. Min Act: -0.1700

Data Index: 943692 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9059. Min Act: -0.1700

Data Index: 252769 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9281. Min Act: -0.1700

Data Index: 3142294 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8737. Min Act: -0.1700

Data Index: 5124910 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9096. Min Act: -0.1700

Data Index: 5026297 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9180. Min Act: -0.1700

Data Index: 8366545 (Open Web Text)

Max Activating Token Index: 80

Text #15

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8933. Min Act: -0.1700

Data Index: 4538725 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8523. Min Act: -0.1700

Data Index: 5626214 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8783. Min Act: -0.1700

Data Index: 1463890 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.8722. Min Act: -0.1700

Data Index: 3073403 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 4.0172. Min Range: -4.0172

Max Act: 3.9299. Min Act: -0.1700

Data Index: 7598760 (Open Web Text)

Max Activating Token Index: 482