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

Dataset: Open Web Text

Neuron 458 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: 1.0287. Min Range: -1.0287

Max Act: 1.0287. Min Act: -0.1700

Data Index: 6290694 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9896. Min Act: -0.1700

Data Index: 8048968 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9919. Min Act: -0.1700

Data Index: 4340521 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9796. Min Act: -0.1700

Data Index: 2484349 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9564. Min Act: -0.1700

Data Index: 8251902 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9532. Min Act: -0.1700

Data Index: 8543865 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9477. Min Act: -0.1655

Data Index: 4601096 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9480. Min Act: -0.1700

Data Index: 5607225 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1700

Data Index: 810205 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1694

Data Index: 1981122 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1628

Data Index: 1338102 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1698

Data Index: 457030 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9437. Min Act: -0.1668

Data Index: 802798 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1697

Data Index: 670262 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1684

Data Index: 1892600 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1700

Data Index: 1150370 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1700

Data Index: 1844401 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1695

Data Index: 427714 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9191. Min Act: -0.1699

Data Index: 1407815 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9352. Min Act: -0.1696

Data Index: 1841550 (Open Web Text)

Max Activating Token Index: 5