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

Dataset: Open Web Text

Neuron 1605 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: 3.8960. Min Range: -3.8960

Max Act: 3.8747. Min Act: -0.1700

Data Index: 6359129 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8960. Min Act: -0.1700

Data Index: 4616392 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8492. Min Act: -0.1700

Data Index: 4310929 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8281. Min Act: -0.1700

Data Index: 8815041 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8355. Min Act: -0.1700

Data Index: 8332166 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8188. Min Act: -0.1700

Data Index: 2842726 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8025. Min Act: -0.1700

Data Index: 4551129 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7822. Min Act: -0.1700

Data Index: 8290032 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7829. Min Act: -0.1700

Data Index: 2130846 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7833. Min Act: -0.1700

Data Index: 1126858 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7914. Min Act: -0.1700

Data Index: 4273235 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1428543 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7985. Min Act: -0.1700

Data Index: 7909165 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7982. Min Act: -0.1700

Data Index: 6693938 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7500. Min Act: -0.1700

Data Index: 3505915 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7463. Min Act: -0.1700

Data Index: 5683427 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7436. Min Act: -0.1700

Data Index: 5753955 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7579. Min Act: -0.1700

Data Index: 6236707 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7729. Min Act: -0.1700

Data Index: 6354442 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7434. Min Act: -0.1700

Data Index: 538905 (Open Web Text)

Max Activating Token Index: 8