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

Dataset: Open Web Text

Neuron 1631 in Layer 2

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: 3.9376. Min Range: -3.9376

Max Act: 3.9376. Min Act: -0.1700

Data Index: 7141646 (Open Web Text)

Max Activating Token Index: 438

Text #1

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8432. Min Act: -0.1700

Data Index: 4039133 (Open Web Text)

Max Activating Token Index: 649

Text #2

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8266. Min Act: -0.1700

Data Index: 5852559 (Open Web Text)

Max Activating Token Index: 110

Text #3

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7870. Min Act: -0.1700

Data Index: 925004 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7957. Min Act: -0.1700

Data Index: 2764931 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.8116. Min Act: -0.1700

Data Index: 907535 (Open Web Text)

Max Activating Token Index: 1007

Text #6

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7749. Min Act: -0.1700

Data Index: 2174574 (Open Web Text)

Max Activating Token Index: 952

Text #7

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7529. Min Act: -0.1700

Data Index: 2087869 (Open Web Text)

Max Activating Token Index: 697

Text #8

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7480. Min Act: -0.1700

Data Index: 6001636 (Open Web Text)

Max Activating Token Index: 198

Text #9

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7598. Min Act: -0.1700

Data Index: 6236043 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7563. Min Act: -0.1700

Data Index: 7291549 (Open Web Text)

Max Activating Token Index: 973

Text #11

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7388. Min Act: -0.1700

Data Index: 2401136 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7464. Min Act: -0.1700

Data Index: 2527732 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7036. Min Act: -0.1700

Data Index: 7977399 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.7339. Min Act: -0.1700

Data Index: 1175830 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.6987. Min Act: -0.1700

Data Index: 3717281 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.6844. Min Act: -0.1700

Data Index: 3259190 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.6707. Min Act: -0.1700

Data Index: 2846571 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.6928. Min Act: -0.1700

Data Index: 4017542 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 3.9376. Min Range: -3.9376

Max Act: 3.6660. Min Act: -0.1700

Data Index: 7836844 (Open Web Text)

Max Activating Token Index: 180