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

Dataset: Open Web Text

Neuron 251 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: 4.0243. Min Range: -4.0243

Max Act: 4.0243. Min Act: -0.1700

Data Index: 6119386 (Open Web Text)

Max Activating Token Index: 319

Text #1

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.9130. Min Act: -0.1700

Data Index: 8185429 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.9205. Min Act: -0.1700

Data Index: 6559115 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.9439. Min Act: -0.1700

Data Index: 5891907 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.9666. Min Act: -0.1700

Data Index: 2235416 (Open Web Text)

Max Activating Token Index: 975

Text #5

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8891. Min Act: -0.1700

Data Index: 3293607 (Open Web Text)

Max Activating Token Index: 797

Text #6

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8506. Min Act: -0.1700

Data Index: 6789927 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8779. Min Act: -0.1700

Data Index: 4838010 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8696. Min Act: -0.1700

Data Index: 5103287 (Open Web Text)

Max Activating Token Index: 316

Text #9

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8397. Min Act: -0.1700

Data Index: 2353291 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8170. Min Act: -0.1700

Data Index: 8178072 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8686. Min Act: -0.1700

Data Index: 5572905 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8845. Min Act: -0.1700

Data Index: 4388533 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8385. Min Act: -0.1700

Data Index: 6706975 (Open Web Text)

Max Activating Token Index: 293

Text #14

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8151. Min Act: -0.1700

Data Index: 7932469 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8648. Min Act: -0.1700

Data Index: 5291425 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.7777. Min Act: -0.1700

Data Index: 2393661 (Open Web Text)

Max Activating Token Index: 534

Text #17

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.8130. Min Act: -0.1700

Data Index: 3322947 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.7983. Min Act: -0.1700

Data Index: 4981564 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.7585. Min Act: -0.1700

Data Index: 5954994 (Open Web Text)

Max Activating Token Index: 508