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

Dataset: Open Web Text

Neuron 2354 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: 3.9722. Min Range: -3.9722

Max Act: 3.9722. Min Act: -0.1700

Data Index: 292596 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.9358. Min Act: -0.1700

Data Index: 598909 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.9400. Min Act: -0.1700

Data Index: 7312636 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8898. Min Act: -0.1700

Data Index: 1730831 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8485. Min Act: -0.1700

Data Index: 7030384 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8797. Min Act: -0.1700

Data Index: 1807175 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8664. Min Act: -0.1700

Data Index: 3078147 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8709. Min Act: -0.1700

Data Index: 4985325 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8611. Min Act: -0.1700

Data Index: 4677158 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8355. Min Act: -0.1700

Data Index: 5444576 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8252. Min Act: -0.1700

Data Index: 6236041 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8310. Min Act: -0.1700

Data Index: 7085379 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7820. Min Act: -0.1700

Data Index: 4622645 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7820. Min Act: -0.1700

Data Index: 3611991 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7937. Min Act: -0.1700

Data Index: 525187 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8082. Min Act: -0.1700

Data Index: 3423944 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7820. Min Act: -0.1700

Data Index: 1460441 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7820. Min Act: -0.1700

Data Index: 3085674 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.8031. Min Act: -0.1700

Data Index: 558350 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7820. Min Act: -0.1700

Data Index: 4985671 (Open Web Text)

Max Activating Token Index: 2