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

Dataset: Open Web Text

Neuron 1520 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: 3.2601. Min Range: -3.2601

Max Act: 3.2601. Min Act: -0.1700

Data Index: 3853173 (Open Web Text)

Max Activating Token Index: 592

Text #1

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.1495. Min Act: -0.1700

Data Index: 7390325 (Open Web Text)

Max Activating Token Index: 896

Text #2

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.1067. Min Act: -0.1700

Data Index: 5531363 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0822. Min Act: -0.1700

Data Index: 7314758 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0455. Min Act: -0.1700

Data Index: 39665 (Open Web Text)

Max Activating Token Index: 974

Text #5

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0430. Min Act: -0.1700

Data Index: 578828 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0513. Min Act: -0.1700

Data Index: 1728822 (Open Web Text)

Max Activating Token Index: 96

Text #7

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0684. Min Act: -0.1700

Data Index: 1313451 (Open Web Text)

Max Activating Token Index: 938

Text #8

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0556. Min Act: -0.1700

Data Index: 4637675 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0419. Min Act: -0.1700

Data Index: 407545 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0339. Min Act: -0.1700

Data Index: 1533777 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0252. Min Act: -0.1700

Data Index: 1236280 (Open Web Text)

Max Activating Token Index: 795

Text #12

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0306. Min Act: -0.1700

Data Index: 854664 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0328. Min Act: -0.1700

Data Index: 671377 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0322. Min Act: -0.1700

Data Index: 4138365 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0065. Min Act: -0.1700

Data Index: 308426 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 3.2601. Min Range: -3.2601

Max Act: 3.0019. Min Act: -0.1700

Data Index: 2589488 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 3.2601. Min Range: -3.2601

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1918999 (Open Web Text)

Max Activating Token Index: 560

Text #18

Max Range: 3.2601. Min Range: -3.2601

Max Act: 2.9974. Min Act: -0.1700

Data Index: 2738228 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 3.2601. Min Range: -3.2601

Max Act: 2.9744. Min Act: -0.1700

Data Index: 2780733 (Open Web Text)

Max Activating Token Index: 681