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

Dataset: Open Web Text

Neuron 1150 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: 13.3039. Min Range: -13.3039

Max Act: 13.3039. Min Act: -0.1700

Data Index: 4325852 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 13.3039. Min Range: -13.3039

Max Act: 13.0086. Min Act: -0.1700

Data Index: 7892449 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.9736. Min Act: -0.1700

Data Index: 5831667 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.9110. Min Act: -0.1700

Data Index: 7189028 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.8943. Min Act: -0.1700

Data Index: 1358448 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.9104. Min Act: -0.1700

Data Index: 1168228 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.8360. Min Act: -0.1700

Data Index: 1109263 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.8827. Min Act: -0.1700

Data Index: 6268692 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.8191. Min Act: -0.1700

Data Index: 1670403 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.9309. Min Act: -0.1700

Data Index: 5805187 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.8896. Min Act: -0.1700

Data Index: 6293931 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.8722. Min Act: -0.1700

Data Index: 5647949 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.6977. Min Act: -0.1700

Data Index: 5972354 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.7674. Min Act: -0.1700

Data Index: 7124652 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.7242. Min Act: -0.1700

Data Index: 7726780 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.7424. Min Act: -0.1700

Data Index: 3303058 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.6818. Min Act: -0.1700

Data Index: 7280787 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.7696. Min Act: -0.1700

Data Index: 2897127 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.7717. Min Act: -0.1700

Data Index: 2071927 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 13.3039. Min Range: -13.3039

Max Act: 12.6617. Min Act: -0.1700

Data Index: 338122 (Open Web Text)

Max Activating Token Index: 1023