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

Dataset: Open Web Text

Neuron 403 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: 4.5381. Min Range: -4.5381

Max Act: 4.5381. Min Act: -0.1700

Data Index: 4146830 (Open Web Text)

Max Activating Token Index: 415

Text #1

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.3172. Min Act: -0.1700

Data Index: 8670438 (Open Web Text)

Max Activating Token Index: 800

Text #2

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.3218. Min Act: -0.1700

Data Index: 7967852 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.2532. Min Act: -0.1700

Data Index: 4178793 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.2561. Min Act: -0.1700

Data Index: 2657250 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.2463. Min Act: -0.1700

Data Index: 3531906 (Open Web Text)

Max Activating Token Index: 690

Text #6

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.2526. Min Act: -0.1700

Data Index: 2583599 (Open Web Text)

Max Activating Token Index: 251

Text #7

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.2177. Min Act: -0.1700

Data Index: 923475 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1503. Min Act: -0.1700

Data Index: 4693499 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1906. Min Act: -0.1700

Data Index: 1071494 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1721. Min Act: -0.1700

Data Index: 6065550 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.2004. Min Act: -0.1700

Data Index: 5772548 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1645. Min Act: -0.1700

Data Index: 20332 (Open Web Text)

Max Activating Token Index: 335

Text #13

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1351. Min Act: -0.1700

Data Index: 8348169 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1985. Min Act: -0.1700

Data Index: 2200298 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1594. Min Act: -0.1700

Data Index: 4518463 (Open Web Text)

Max Activating Token Index: 155

Text #16

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1321. Min Act: -0.1700

Data Index: 5754744 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1690. Min Act: -0.1700

Data Index: 6404204 (Open Web Text)

Max Activating Token Index: 704

Text #18

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1809. Min Act: -0.1700

Data Index: 405736 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 4.5381. Min Range: -4.5381

Max Act: 4.1408. Min Act: -0.1700

Data Index: 1288566 (Open Web Text)

Max Activating Token Index: 600