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

Dataset: Open Web Text

Neuron 1385 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: 1.8035. Min Range: -1.8035

Max Act: 1.8035. Min Act: -0.1094

Data Index: 8028020 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7905. Min Act: -0.1094

Data Index: 2696282 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7719. Min Act: -0.1094

Data Index: 525099 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7501. Min Act: -0.1094

Data Index: 8521244 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7301. Min Act: -0.1094

Data Index: 4834327 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7166. Min Act: -0.1094

Data Index: 919932 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7334. Min Act: -0.1094

Data Index: 7944564 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7239. Min Act: -0.1094

Data Index: 5049814 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7171. Min Act: -0.1094

Data Index: 6471559 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7169. Min Act: -0.1094

Data Index: 4701256 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7037. Min Act: -0.1094

Data Index: 6787170 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7064. Min Act: -0.1094

Data Index: 6546750 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7127. Min Act: -0.1109

Data Index: 6146825 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7101. Min Act: -0.1094

Data Index: 4153966 (Open Web Text)

Max Activating Token Index: 1010

Text #14

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7132. Min Act: -0.1094

Data Index: 8558270 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6981. Min Act: -0.1094

Data Index: 4650857 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6978. Min Act: -0.1094

Data Index: 2235101 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6982. Min Act: -0.1094

Data Index: 7707350 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7082. Min Act: -0.1094

Data Index: 2261340 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6961. Min Act: -0.1094

Data Index: 467960 (Open Web Text)

Max Activating Token Index: 983