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

Dataset: Open Web Text

Neuron 3064 in Layer 6

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: 3.3018. Min Range: -3.3018

Max Act: 3.3018. Min Act: -0.1700

Data Index: 1723787 (Open Web Text)

Max Activating Token Index: 968

Text #1

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2666. Min Act: -0.1700

Data Index: 3244710 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2561. Min Act: -0.1700

Data Index: 4362087 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1723788 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2279. Min Act: -0.1700

Data Index: 2160190 (Open Web Text)

Max Activating Token Index: 976

Text #5

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.2266. Min Act: -0.1700

Data Index: 8641393 (Open Web Text)

Max Activating Token Index: 990

Text #6

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1604. Min Act: -0.1700

Data Index: 1967416 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1631. Min Act: -0.1700

Data Index: 5366873 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1136. Min Act: -0.1700

Data Index: 1962123 (Open Web Text)

Max Activating Token Index: 980

Text #9

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1197. Min Act: -0.1700

Data Index: 8641392 (Open Web Text)

Max Activating Token Index: 873

Text #10

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1190. Min Act: -0.1700

Data Index: 6826814 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1103. Min Act: -0.1700

Data Index: 3730101 (Open Web Text)

Max Activating Token Index: 985

Text #12

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1013. Min Act: -0.1700

Data Index: 6445690 (Open Web Text)

Max Activating Token Index: 970

Text #13

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1078. Min Act: -0.1700

Data Index: 1744872 (Open Web Text)

Max Activating Token Index: 980

Text #14

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.0986. Min Act: -0.1700

Data Index: 3140093 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1171. Min Act: -0.1700

Data Index: 2371790 (Open Web Text)

Max Activating Token Index: 943

Text #16

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.1175. Min Act: -0.1700

Data Index: 428292 (Open Web Text)

Max Activating Token Index: 997

Text #17

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.0839. Min Act: -0.1700

Data Index: 6618188 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.0830. Min Act: -0.1700

Data Index: 4928149 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 3.3018. Min Range: -3.3018

Max Act: 3.0919. Min Act: -0.1700

Data Index: 3097032 (Open Web Text)

Max Activating Token Index: 970