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

Dataset: Open Web Text

Neuron 2903 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: 1.9270. Min Range: -1.9270

Max Act: 1.9270. Min Act: -0.1700

Data Index: 4667928 (Open Web Text)

Max Activating Token Index: 463

Text #1

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.8806. Min Act: -0.1695

Data Index: 7437434 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.8216. Min Act: -0.1698

Data Index: 4003013 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7859. Min Act: -0.1700

Data Index: 7929457 (Open Web Text)

Max Activating Token Index: 795

Text #4

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7805. Min Act: -0.1695

Data Index: 1388657 (Open Web Text)

Max Activating Token Index: 967

Text #5

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7556. Min Act: -0.1698

Data Index: 8613807 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7351. Min Act: -0.1700

Data Index: 76001 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7360. Min Act: -0.1700

Data Index: 2945094 (Open Web Text)

Max Activating Token Index: 982

Text #8

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7294. Min Act: -0.1700

Data Index: 1913697 (Open Web Text)

Max Activating Token Index: 836

Text #9

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7436. Min Act: -0.1695

Data Index: 4871405 (Open Web Text)

Max Activating Token Index: 825

Text #10

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7224. Min Act: -0.1700

Data Index: 7437433 (Open Web Text)

Max Activating Token Index: 997

Text #11

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7192. Min Act: -0.1700

Data Index: 7349691 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7161. Min Act: -0.1700

Data Index: 8703246 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7290. Min Act: -0.1695

Data Index: 3672650 (Open Web Text)

Max Activating Token Index: 711

Text #14

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7119. Min Act: -0.1700

Data Index: 4984770 (Open Web Text)

Max Activating Token Index: 992

Text #15

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7039. Min Act: -0.1700

Data Index: 1747990 (Open Web Text)

Max Activating Token Index: 806

Text #16

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7255. Min Act: -0.1700

Data Index: 1228761 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.7125. Min Act: -0.1700

Data Index: 2508166 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.6885. Min Act: -0.1700

Data Index: 2928981 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 1.9270. Min Range: -1.9270

Max Act: 1.6949. Min Act: -0.1700

Data Index: 6026467 (Open Web Text)

Max Activating Token Index: 1017