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

Dataset: Open Web Text

Neuron 2653 in Layer 2

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: 1.8019. Min Range: -1.8019

Max Act: 1.8019. Min Act: -0.1700

Data Index: 5398112 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.8018. Min Act: -0.1696

Data Index: 804721 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7679. Min Act: -0.1700

Data Index: 1782781 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7460. Min Act: -0.1694

Data Index: 3014528 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7337. Min Act: -0.1695

Data Index: 7461559 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7422. Min Act: -0.1671

Data Index: 1139963 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7205. Min Act: -0.1697

Data Index: 1165132 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7078. Min Act: -0.1699

Data Index: 7741272 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7192. Min Act: -0.1689

Data Index: 4095102 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7015. Min Act: -0.1700

Data Index: 4806206 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6993. Min Act: -0.1700

Data Index: 520772 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6893. Min Act: -0.1682

Data Index: 4896702 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.7090. Min Act: -0.1700

Data Index: 2734993 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6841. Min Act: -0.1700

Data Index: 2510590 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6787. Min Act: -0.1677

Data Index: 5737626 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6672. Min Act: -0.1700

Data Index: 4256888 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6500. Min Act: -0.1692

Data Index: 7268226 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6552. Min Act: -0.1699

Data Index: 4488038 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6432. Min Act: -0.1698

Data Index: 7368562 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.6466. Min Act: -0.1692

Data Index: 7664363 (Open Web Text)

Max Activating Token Index: 5