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

Dataset: Open Web Text

Neuron 429 in Layer 0

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: 5.2970. Min Range: -5.2970

Max Act: 5.2970. Min Act: -0.1700

Data Index: 4925179 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2721. Min Act: -0.1700

Data Index: 2183178 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2293. Min Act: -0.1700

Data Index: 5226163 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2339. Min Act: -0.1700

Data Index: 1322891 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2293. Min Act: -0.1700

Data Index: 1362660 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2176. Min Act: -0.1700

Data Index: 4481434 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2208. Min Act: -0.1700

Data Index: 2477047 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2249. Min Act: -0.1700

Data Index: 7757896 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2066. Min Act: -0.1700

Data Index: 2516447 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1928. Min Act: -0.1700

Data Index: 3411027 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2036. Min Act: -0.1700

Data Index: 1411518 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1892. Min Act: -0.1700

Data Index: 7259165 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2116. Min Act: -0.1700

Data Index: 5384897 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.2068. Min Act: -0.1700

Data Index: 816395 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1631. Min Act: -0.1700

Data Index: 1472650 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1766. Min Act: -0.1700

Data Index: 3581145 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1590. Min Act: -0.1700

Data Index: 3654894 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1811. Min Act: -0.1700

Data Index: 952490 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1620. Min Act: -0.1700

Data Index: 3783761 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.1620. Min Act: -0.1700

Data Index: 213996 (Open Web Text)

Max Activating Token Index: 4