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

Dataset: Open Web Text

Neuron 2598 in Layer 1

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: 1.0644. Min Range: -1.0644

Max Act: 1.0644. Min Act: -0.1673

Data Index: 7806493 (Open Web Text)

Max Activating Token Index: 698

Text #1

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0457. Min Act: -0.1678

Data Index: 5566437 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0373. Min Act: -0.1607

Data Index: 821199 (Open Web Text)

Max Activating Token Index: 732

Text #3

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0492. Min Act: -0.1532

Data Index: 2511084 (Open Web Text)

Max Activating Token Index: 746

Text #4

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0299. Min Act: -0.1520

Data Index: 6605746 (Open Web Text)

Max Activating Token Index: 759

Text #5

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0266. Min Act: -0.1560

Data Index: 7395695 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0101. Min Act: -0.1539

Data Index: 3887165 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0139. Min Act: -0.1693

Data Index: 8219279 (Open Web Text)

Max Activating Token Index: 637

Text #8

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9966. Min Act: -0.1642

Data Index: 821200 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0054. Min Act: -0.1518

Data Index: 448286 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0059. Min Act: -0.1613

Data Index: 2005384 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9879. Min Act: -0.1614

Data Index: 1152556 (Open Web Text)

Max Activating Token Index: 691

Text #12

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9987. Min Act: -0.1627

Data Index: 4797123 (Open Web Text)

Max Activating Token Index: 725

Text #13

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9969. Min Act: -0.1646

Data Index: 2005382 (Open Web Text)

Max Activating Token Index: 719

Text #14

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9878. Min Act: -0.1594

Data Index: 8311417 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9889. Min Act: -0.1594

Data Index: 1283155 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9885. Min Act: -0.1505

Data Index: 821198 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9911. Min Act: -0.1608

Data Index: 2753531 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9825. Min Act: -0.1643

Data Index: 8311418 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9861. Min Act: -0.1697

Data Index: 4892467 (Open Web Text)

Max Activating Token Index: 753