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

Dataset: Open Web Text

Neuron 2578 in Layer 3

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: 1.0048. Min Range: -1.0048

Max Act: 1.0048. Min Act: -0.1700

Data Index: 5851366 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9888. Min Act: -0.1700

Data Index: 6381418 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9442. Min Act: -0.1700

Data Index: 1120922 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9564. Min Act: -0.1700

Data Index: 7634223 (Open Web Text)

Max Activating Token Index: 136

Text #4

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9182. Min Act: -0.1700

Data Index: 2230125 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9275. Min Act: -0.1700

Data Index: 323418 (Open Web Text)

Max Activating Token Index: 145

Text #6

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9239. Min Act: -0.1700

Data Index: 4649444 (Open Web Text)

Max Activating Token Index: 82

Text #7

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9151. Min Act: -0.1700

Data Index: 7805117 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9212. Min Act: -0.1697

Data Index: 666652 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9059. Min Act: -0.1700

Data Index: 5268900 (Open Web Text)

Max Activating Token Index: 82

Text #10

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9017. Min Act: -0.1700

Data Index: 2045038 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9010. Min Act: -0.1700

Data Index: 1649179 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9015. Min Act: -0.1700

Data Index: 80775 (Open Web Text)

Max Activating Token Index: 116

Text #13

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9013. Min Act: -0.1700

Data Index: 7050816 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9111. Min Act: -0.1700

Data Index: 2673448 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9050. Min Act: -0.1700

Data Index: 5773179 (Open Web Text)

Max Activating Token Index: 93

Text #16

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9017. Min Act: -0.1698

Data Index: 5011826 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9026. Min Act: -0.1678

Data Index: 3099357 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8971. Min Act: -0.1700

Data Index: 2002910 (Open Web Text)

Max Activating Token Index: 96

Text #19

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8953. Min Act: -0.1700

Data Index: 4933181 (Open Web Text)

Max Activating Token Index: 130