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

Dataset: Open Web Text

Neuron 1490 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: 4.5014. Min Range: -4.5014

Max Act: 4.5014. Min Act: -0.1700

Data Index: 4895509 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.4141. Min Act: -0.1700

Data Index: 2790252 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.4348. Min Act: -0.1700

Data Index: 7304761 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3519. Min Act: -0.1700

Data Index: 7988823 (Open Web Text)

Max Activating Token Index: 251

Text #4

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3610. Min Act: -0.1700

Data Index: 2356252 (Open Web Text)

Max Activating Token Index: 676

Text #5

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3598. Min Act: -0.1700

Data Index: 150468 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3106. Min Act: -0.1700

Data Index: 8095348 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2921. Min Act: -0.1700

Data Index: 3214012 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3247. Min Act: -0.1700

Data Index: 360345 (Open Web Text)

Max Activating Token Index: 1008

Text #9

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.3024. Min Act: -0.1700

Data Index: 1860835 (Open Web Text)

Max Activating Token Index: 1018

Text #10

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2804. Min Act: -0.1700

Data Index: 5765032 (Open Web Text)

Max Activating Token Index: 139

Text #11

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2614. Min Act: -0.1700

Data Index: 5266686 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2362. Min Act: -0.1700

Data Index: 1612277 (Open Web Text)

Max Activating Token Index: 625

Text #13

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2463. Min Act: -0.1700

Data Index: 5711794 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2102. Min Act: -0.1700

Data Index: 1415860 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.2346. Min Act: -0.1700

Data Index: 7156416 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.1394. Min Act: -0.1700

Data Index: 1992338 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.1819. Min Act: -0.1700

Data Index: 1590306 (Open Web Text)

Max Activating Token Index: 237

Text #18

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.1716. Min Act: -0.1700

Data Index: 7881106 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 4.5014. Min Range: -4.5014

Max Act: 4.1726. Min Act: -0.1700

Data Index: 3471002 (Open Web Text)

Max Activating Token Index: 246