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

Dataset: Open Web Text

Neuron 2877 in Layer 2

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: 1.6653. Min Range: -1.6653

Max Act: 1.6653. Min Act: -0.1700

Data Index: 105313 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6344. Min Act: -0.1700

Data Index: 5795967 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6296. Min Act: -0.1700

Data Index: 3240370 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6278. Min Act: -0.1700

Data Index: 7451129 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6224. Min Act: -0.1700

Data Index: 3853345 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6130. Min Act: -0.1700

Data Index: 6178337 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6047. Min Act: -0.1700

Data Index: 5152898 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5889. Min Act: -0.1700

Data Index: 5021755 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6034. Min Act: -0.1700

Data Index: 1032880 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6103. Min Act: -0.1700

Data Index: 3270725 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5996. Min Act: -0.1700

Data Index: 7241253 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5952. Min Act: -0.1700

Data Index: 4121184 (Open Web Text)

Max Activating Token Index: 914

Text #12

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6167. Min Act: -0.1699

Data Index: 2956403 (Open Web Text)

Max Activating Token Index: 750

Text #13

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5962. Min Act: -0.1700

Data Index: 7851153 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5895. Min Act: -0.1700

Data Index: 7305217 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5967. Min Act: -0.1700

Data Index: 558918 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5950. Min Act: -0.1700

Data Index: 7003096 (Open Web Text)

Max Activating Token Index: 976

Text #17

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5910. Min Act: -0.1700

Data Index: 732346 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.6061. Min Act: -0.1700

Data Index: 2821226 (Open Web Text)

Max Activating Token Index: 366

Text #19

Max Range: 1.6653. Min Range: -1.6653

Max Act: 1.5870. Min Act: -0.1700

Data Index: 2472834 (Open Web Text)

Max Activating Token Index: 4