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

Dataset: Open Web Text

Neuron 1463 in Layer 6

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: 5.5608. Min Range: -5.5608

Max Act: 5.5608. Min Act: -0.1700

Data Index: 3668360 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.3361. Min Act: -0.1700

Data Index: 276276 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.3114. Min Act: -0.1700

Data Index: 4279715 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.2821. Min Act: -0.1700

Data Index: 8039479 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.2628. Min Act: -0.1700

Data Index: 8400200 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.2279. Min Act: -0.1700

Data Index: 1514739 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.2681. Min Act: -0.1700

Data Index: 943949 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1712. Min Act: -0.1700

Data Index: 4424757 (Open Web Text)

Max Activating Token Index: 848

Text #8

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1927. Min Act: -0.1700

Data Index: 2357596 (Open Web Text)

Max Activating Token Index: 986

Text #9

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1345. Min Act: -0.1700

Data Index: 4308610 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1183. Min Act: -0.1700

Data Index: 6289263 (Open Web Text)

Max Activating Token Index: 833

Text #11

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.0812. Min Act: -0.1700

Data Index: 6866641 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.0793. Min Act: -0.1700

Data Index: 415310 (Open Web Text)

Max Activating Token Index: 164

Text #13

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.0887. Min Act: -0.1700

Data Index: 1852680 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1394. Min Act: -0.1700

Data Index: 6189781 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.0530. Min Act: -0.1700

Data Index: 5373990 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.0829. Min Act: -0.1700

Data Index: 2904829 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1026. Min Act: -0.1700

Data Index: 5505084 (Open Web Text)

Max Activating Token Index: 752

Text #18

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1097. Min Act: -0.1700

Data Index: 4424759 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 5.5608. Min Range: -5.5608

Max Act: 5.1024. Min Act: -0.1700

Data Index: 5904121 (Open Web Text)

Max Activating Token Index: 874