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

Dataset: Open Web Text

Neuron 2516 in Layer 0

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: 1.6442. Min Range: -1.6442

Max Act: 1.6442. Min Act: -0.1483

Data Index: 7425491 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.6259. Min Act: -0.1696

Data Index: 1757019 (Open Web Text)

Max Activating Token Index: 414

Text #2

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.6201. Min Act: -0.1637

Data Index: 1123908 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.6079. Min Act: -0.1700

Data Index: 5244456 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5917. Min Act: -0.1688

Data Index: 6895319 (Open Web Text)

Max Activating Token Index: 1002

Text #5

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5994. Min Act: -0.1700

Data Index: 26153 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5895. Min Act: -0.1693

Data Index: 6840421 (Open Web Text)

Max Activating Token Index: 733

Text #7

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5872. Min Act: -0.1689

Data Index: 5769315 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5851. Min Act: -0.1656

Data Index: 7589357 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5891. Min Act: -0.1439

Data Index: 1011733 (Open Web Text)

Max Activating Token Index: 149

Text #10

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5759. Min Act: -0.1699

Data Index: 4904531 (Open Web Text)

Max Activating Token Index: 560

Text #11

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5740. Min Act: -0.1432

Data Index: 2820947 (Open Web Text)

Max Activating Token Index: 776

Text #12

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5778. Min Act: -0.1678

Data Index: 778741 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5753. Min Act: -0.1689

Data Index: 408955 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5712. Min Act: -0.1697

Data Index: 216066 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5708. Min Act: -0.1700

Data Index: 2776464 (Open Web Text)

Max Activating Token Index: 626

Text #16

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5642. Min Act: -0.1699

Data Index: 433867 (Open Web Text)

Max Activating Token Index: 279

Text #17

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5629. Min Act: -0.1690

Data Index: 4385484 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5627. Min Act: -0.1700

Data Index: 4442141 (Open Web Text)

Max Activating Token Index: 714

Text #19

Max Range: 1.6442. Min Range: -1.6442

Max Act: 1.5575. Min Act: -0.1685

Data Index: 1467801 (Open Web Text)

Max Activating Token Index: 709