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

Dataset: Open Web Text

Neuron 1995 in Layer 3

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: 2.4361. Min Range: -2.4361

Max Act: 2.4361. Min Act: -0.1689

Data Index: 2269039 (Open Web Text)

Max Activating Token Index: 130

Text #1

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.4093. Min Act: -0.1653

Data Index: 6346671 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3897. Min Act: -0.1700

Data Index: 1492793 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3646. Min Act: -0.1638

Data Index: 3966968 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3541. Min Act: -0.1700

Data Index: 5559767 (Open Web Text)

Max Activating Token Index: 31

Text #5

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3547. Min Act: -0.1638

Data Index: 3523006 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3631. Min Act: -0.1621

Data Index: 4621617 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3833. Min Act: -0.1700

Data Index: 4470366 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3628. Min Act: -0.1691

Data Index: 6509819 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3633. Min Act: -0.1532

Data Index: 8388240 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3338. Min Act: -0.1640

Data Index: 5365907 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3665. Min Act: -0.1700

Data Index: 3085252 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3550. Min Act: -0.1692

Data Index: 2819799 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3535. Min Act: -0.1698

Data Index: 7661653 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3522. Min Act: -0.1700

Data Index: 4305336 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3442. Min Act: -0.1651

Data Index: 4280456 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3523. Min Act: -0.1654

Data Index: 5604244 (Open Web Text)

Max Activating Token Index: 152

Text #17

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3565. Min Act: -0.1700

Data Index: 199795 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3491. Min Act: -0.1684

Data Index: 3031937 (Open Web Text)

Max Activating Token Index: 61

Text #19

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.3304. Min Act: -0.1696

Data Index: 4961353 (Open Web Text)

Max Activating Token Index: 846