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

Dataset: Open Web Text

Neuron 2582 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: 1.1875. Min Range: -1.1875

Max Act: 1.1875. Min Act: -0.0988

Data Index: 7289533 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1725. Min Act: -0.1046

Data Index: 2185728 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1552. Min Act: -0.0510

Data Index: 6220142 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1512. Min Act: -0.1009

Data Index: 7289530 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1460. Min Act: -0.1048

Data Index: 3784887 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1120. Min Act: 0.0200

Data Index: 7131353 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1082. Min Act: -0.0938

Data Index: 8393867 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1060. Min Act: -0.1071

Data Index: 7899099 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1041. Min Act: -0.0809

Data Index: 8483246 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1089. Min Act: -0.0843

Data Index: 7598396 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1032. Min Act: -0.1005

Data Index: 3180070 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0986. Min Act: -0.0943

Data Index: 6855815 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0985. Min Act: -0.0898

Data Index: 4556378 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0936. Min Act: -0.0548

Data Index: 4431960 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0976. Min Act: -0.0798

Data Index: 5846668 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0939. Min Act: -0.0976

Data Index: 3704202 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0968. Min Act: -0.0894

Data Index: 4182075 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0917. Min Act: -0.0900

Data Index: 2791030 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0900. Min Act: -0.0259

Data Index: 641345 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0887. Min Act: -0.0878

Data Index: 2838376 (Open Web Text)

Max Activating Token Index: 1023