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

Dataset: Open Web Text

Neuron 1517 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: 1.7778. Min Range: -1.7778

Max Act: 1.7768. Min Act: -0.1693

Data Index: 1779138 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7778. Min Act: -0.1521

Data Index: 4175740 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7728. Min Act: -0.1698

Data Index: 4293609 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7619. Min Act: -0.1521

Data Index: 6335751 (Open Web Text)

Max Activating Token Index: 385

Text #4

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7607. Min Act: -0.1521

Data Index: 7479156 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7542. Min Act: -0.1700

Data Index: 5440377 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7544. Min Act: -0.1645

Data Index: 78104 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7532. Min Act: -0.1649

Data Index: 1236897 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7371. Min Act: -0.1700

Data Index: 7154258 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7413. Min Act: -0.1693

Data Index: 6177942 (Open Web Text)

Max Activating Token Index: 683

Text #10

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7236. Min Act: -0.1681

Data Index: 6306244 (Open Web Text)

Max Activating Token Index: 306

Text #11

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7221. Min Act: -0.1696

Data Index: 8725632 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7180. Min Act: -0.1565

Data Index: 498877 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7137. Min Act: -0.1699

Data Index: 12491 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7173. Min Act: -0.1572

Data Index: 7479153 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7131. Min Act: -0.1521

Data Index: 3371525 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7004. Min Act: -0.1690

Data Index: 5182795 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7020. Min Act: -0.1642

Data Index: 511866 (Open Web Text)

Max Activating Token Index: 982

Text #18

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.7025. Min Act: -0.1653

Data Index: 5519160 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 1.7778. Min Range: -1.7778

Max Act: 1.6910. Min Act: -0.1698

Data Index: 4154138 (Open Web Text)

Max Activating Token Index: 144