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

Dataset: Open Web Text

Neuron 1535 in Layer 4

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: 2.2846. Min Range: -2.2846

Max Act: 2.2846. Min Act: -0.1698

Data Index: 3565175 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2771. Min Act: -0.1684

Data Index: 6359594 (Open Web Text)

Max Activating Token Index: 932

Text #2

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2555. Min Act: -0.1700

Data Index: 2636029 (Open Web Text)

Max Activating Token Index: 784

Text #3

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2221. Min Act: -0.1564

Data Index: 5942363 (Open Web Text)

Max Activating Token Index: 412

Text #4

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2507. Min Act: -0.1700

Data Index: 1775303 (Open Web Text)

Max Activating Token Index: 1004

Text #5

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2329. Min Act: -0.1658

Data Index: 1223679 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2243. Min Act: -0.1700

Data Index: 8503013 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2076. Min Act: -0.1693

Data Index: 7990189 (Open Web Text)

Max Activating Token Index: 275

Text #8

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2106. Min Act: -0.1700

Data Index: 3565174 (Open Web Text)

Max Activating Token Index: 938

Text #9

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2159. Min Act: -0.1688

Data Index: 2242815 (Open Web Text)

Max Activating Token Index: 831

Text #10

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1940. Min Act: -0.1699

Data Index: 3627262 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1935. Min Act: -0.1700

Data Index: 1103703 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1879. Min Act: -0.1698

Data Index: 3662800 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1966. Min Act: -0.1696

Data Index: 4449385 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2015. Min Act: -0.1695

Data Index: 4450861 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1860. Min Act: -0.1688

Data Index: 53009 (Open Web Text)

Max Activating Token Index: 756

Text #16

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1870. Min Act: -0.1700

Data Index: 6892281 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1860. Min Act: -0.1700

Data Index: 6893796 (Open Web Text)

Max Activating Token Index: 993

Text #18

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.2013. Min Act: -0.1699

Data Index: 7509119 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 2.2846. Min Range: -2.2846

Max Act: 2.1857. Min Act: -0.1672

Data Index: 1405440 (Open Web Text)

Max Activating Token Index: 986