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

Dataset: Open Web Text

Neuron 1942 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: 4.8305. Min Range: -4.8305

Max Act: 4.8305. Min Act: -0.1700

Data Index: 8592969 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.7919. Min Act: -0.1700

Data Index: 3751322 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.7813. Min Act: -0.1700

Data Index: 2502305 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.7416. Min Act: -0.1700

Data Index: 3715523 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.5997. Min Act: -0.1700

Data Index: 4222641 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.5449. Min Act: -0.1700

Data Index: 5302639 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.5211. Min Act: -0.1700

Data Index: 6948228 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.5145. Min Act: -0.1700

Data Index: 1655273 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.5085. Min Act: -0.1700

Data Index: 7904629 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.4833. Min Act: -0.1700

Data Index: 6505817 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.4797. Min Act: -0.1700

Data Index: 5915573 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3891. Min Act: -0.1700

Data Index: 1618086 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.4027. Min Act: -0.1700

Data Index: 5379946 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.4269. Min Act: -0.1700

Data Index: 1431524 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3716. Min Act: -0.1700

Data Index: 5783403 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3741. Min Act: -0.1700

Data Index: 1093742 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3752. Min Act: -0.1700

Data Index: 3777126 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3697. Min Act: -0.1700

Data Index: 6133382 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3797. Min Act: -0.1700

Data Index: 1849847 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.8305. Min Range: -4.8305

Max Act: 4.3524. Min Act: -0.1700

Data Index: 3922150 (Open Web Text)

Max Activating Token Index: 1023