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

Dataset: Open Web Text

Neuron 2413 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: 1.8482. Min Range: -1.8482

Max Act: 1.8453. Min Act: -0.1700

Data Index: 7210346 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8171. Min Act: -0.1650

Data Index: 5347962 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8482. Min Act: -0.1582

Data Index: 6481767 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8031. Min Act: -0.1699

Data Index: 9586 (Open Web Text)

Max Activating Token Index: 731

Text #4

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8207. Min Act: -0.1623

Data Index: 1851168 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7751. Min Act: -0.1697

Data Index: 2772737 (Open Web Text)

Max Activating Token Index: 872

Text #6

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7561. Min Act: -0.1586

Data Index: 6317750 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7599. Min Act: -0.1653

Data Index: 6794490 (Open Web Text)

Max Activating Token Index: 807

Text #8

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7777. Min Act: -0.1602

Data Index: 7161745 (Open Web Text)

Max Activating Token Index: 848

Text #9

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7594. Min Act: -0.1696

Data Index: 7926153 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7568. Min Act: -0.1688

Data Index: 2552372 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7625. Min Act: -0.1661

Data Index: 3317701 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7779. Min Act: -0.1486

Data Index: 5902571 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7447. Min Act: -0.1689

Data Index: 8464142 (Open Web Text)

Max Activating Token Index: 836

Text #14

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7422. Min Act: -0.1700

Data Index: 1859504 (Open Web Text)

Max Activating Token Index: 125

Text #15

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7380. Min Act: -0.1538

Data Index: 7914361 (Open Web Text)

Max Activating Token Index: 787

Text #16

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7442. Min Act: -0.1670

Data Index: 6481768 (Open Web Text)

Max Activating Token Index: 557

Text #17

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7087. Min Act: -0.1668

Data Index: 3795163 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7138. Min Act: -0.1680

Data Index: 7639608 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7202. Min Act: -0.1698

Data Index: 9587 (Open Web Text)

Max Activating Token Index: 823