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

Dataset: Open Web Text

Neuron 2472 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: 2.2828. Min Range: -2.2828

Max Act: 2.2828. Min Act: -0.1700

Data Index: 5503200 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.2559. Min Act: -0.1700

Data Index: 283689 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.2499. Min Act: -0.1700

Data Index: 6998053 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.2295. Min Act: -0.1700

Data Index: 2513905 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.2204. Min Act: -0.1700

Data Index: 869007 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1892. Min Act: -0.1700

Data Index: 3328305 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1999. Min Act: -0.1700

Data Index: 3980310 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.2012. Min Act: -0.1700

Data Index: 489507 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1800. Min Act: -0.1700

Data Index: 3744934 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1829. Min Act: -0.1700

Data Index: 7630356 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1894. Min Act: -0.1700

Data Index: 5025542 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1806. Min Act: -0.1700

Data Index: 1224414 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1843. Min Act: -0.1700

Data Index: 106881 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1831. Min Act: -0.1700

Data Index: 6976419 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1760. Min Act: -0.1700

Data Index: 1862995 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1841. Min Act: -0.1700

Data Index: 1940738 (Open Web Text)

Max Activating Token Index: 129

Text #16

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1910. Min Act: -0.1700

Data Index: 8451524 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1794. Min Act: -0.1700

Data Index: 8248301 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1660. Min Act: -0.1700

Data Index: 920888 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 2.2828. Min Range: -2.2828

Max Act: 2.1556. Min Act: -0.1700

Data Index: 7413703 (Open Web Text)

Max Activating Token Index: 1022