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

Dataset: Open Web Text

Neuron 1884 in Layer 5

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: 4.6288. Min Range: -4.6288

Max Act: 4.6288. Min Act: -0.1700

Data Index: 254824 (Open Web Text)

Max Activating Token Index: 968

Text #1

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.6127. Min Act: -0.1700

Data Index: 1570023 (Open Web Text)

Max Activating Token Index: 681

Text #2

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.6274. Min Act: -0.1700

Data Index: 1745015 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5812. Min Act: -0.1700

Data Index: 8559326 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5513. Min Act: -0.1700

Data Index: 4933049 (Open Web Text)

Max Activating Token Index: 322

Text #5

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5486. Min Act: -0.1700

Data Index: 8146767 (Open Web Text)

Max Activating Token Index: 777

Text #6

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5495. Min Act: -0.1700

Data Index: 3785444 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5665. Min Act: -0.1700

Data Index: 7045545 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5487. Min Act: -0.1700

Data Index: 8575317 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5285. Min Act: -0.1700

Data Index: 7529077 (Open Web Text)

Max Activating Token Index: 720

Text #10

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5158. Min Act: -0.1700

Data Index: 6640941 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5242. Min Act: -0.1700

Data Index: 1141547 (Open Web Text)

Max Activating Token Index: 611

Text #12

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.4734. Min Act: -0.1700

Data Index: 4617548 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.4754. Min Act: -0.1700

Data Index: 6017293 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.4850. Min Act: -0.1700

Data Index: 6412969 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.4895. Min Act: -0.1700

Data Index: 252070 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.4877. Min Act: -0.1700

Data Index: 6536177 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5201. Min Act: -0.1700

Data Index: 3507366 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5110. Min Act: -0.1700

Data Index: 2759013 (Open Web Text)

Max Activating Token Index: 386

Text #19

Max Range: 4.6288. Min Range: -4.6288

Max Act: 4.5015. Min Act: -0.1700

Data Index: 4799370 (Open Web Text)

Max Activating Token Index: 855