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

Dataset: Open Web Text

Neuron 1315 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: 1.2665. Min Range: -1.2665

Max Act: 1.2665. Min Act: -0.1699

Data Index: 7943479 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2474. Min Act: -0.1700

Data Index: 5637189 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2350. Min Act: -0.1700

Data Index: 8056455 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2261. Min Act: -0.1691

Data Index: 5602927 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2208. Min Act: -0.1686

Data Index: 1558185 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2047. Min Act: -0.1698

Data Index: 2795106 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2102. Min Act: -0.1698

Data Index: 3129476 (Open Web Text)

Max Activating Token Index: 380

Text #7

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2158. Min Act: -0.1700

Data Index: 4358048 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.2005. Min Act: -0.1692

Data Index: 5716626 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1857. Min Act: -0.1700

Data Index: 7394459 (Open Web Text)

Max Activating Token Index: 53

Text #10

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1878. Min Act: -0.1698

Data Index: 6493602 (Open Web Text)

Max Activating Token Index: 120

Text #11

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1895. Min Act: -0.1699

Data Index: 5420930 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1916. Min Act: -0.1700

Data Index: 6097106 (Open Web Text)

Max Activating Token Index: 809

Text #13

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1870. Min Act: -0.1696

Data Index: 4715718 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1790. Min Act: -0.1660

Data Index: 6052054 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1824. Min Act: -0.1700

Data Index: 6097086 (Open Web Text)

Max Activating Token Index: 582

Text #16

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1786. Min Act: -0.1693

Data Index: 8336523 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1812. Min Act: -0.1700

Data Index: 8033463 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1821. Min Act: -0.1698

Data Index: 3886753 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 1.2665. Min Range: -1.2665

Max Act: 1.1670. Min Act: -0.1686

Data Index: 524973 (Open Web Text)

Max Activating Token Index: 269