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

Dataset: Open Web Text

Neuron 2333 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: 5.0097. Min Range: -5.0097

Max Act: 5.0097. Min Act: -0.1700

Data Index: 1611691 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9852. Min Act: -0.1700

Data Index: 7003649 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9770. Min Act: -0.1700

Data Index: 2032038 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9882. Min Act: -0.1700

Data Index: 690502 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9797. Min Act: -0.1700

Data Index: 1922884 (Open Web Text)

Max Activating Token Index: 843

Text #5

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9835. Min Act: -0.1700

Data Index: 857369 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9585. Min Act: -0.1700

Data Index: 2207177 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9533. Min Act: -0.1700

Data Index: 7440035 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9518. Min Act: -0.1700

Data Index: 971443 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9277. Min Act: -0.1700

Data Index: 1155461 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9170. Min Act: -0.1700

Data Index: 7618187 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9137. Min Act: -0.1700

Data Index: 5917149 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9271. Min Act: -0.1700

Data Index: 7932779 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9126. Min Act: -0.1700

Data Index: 6412367 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9238. Min Act: -0.1700

Data Index: 7509415 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9338. Min Act: -0.1700

Data Index: 7384646 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.9181. Min Act: -0.1700

Data Index: 3219352 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.8762. Min Act: -0.1700

Data Index: 7386736 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.8718. Min Act: -0.1700

Data Index: 4088650 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 5.0097. Min Range: -5.0097

Max Act: 4.8878. Min Act: -0.1700

Data Index: 1439278 (Open Web Text)

Max Activating Token Index: 5