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

Dataset: Open Web Text

Neuron 2442 in Layer 1

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: 1.8237. Min Range: -1.8237

Max Act: 1.8237. Min Act: -0.1700

Data Index: 4585815 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7977. Min Act: -0.1700

Data Index: 3240784 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7966. Min Act: -0.1698

Data Index: 2081623 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7854. Min Act: -0.1700

Data Index: 8092132 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7728. Min Act: -0.1700

Data Index: 147504 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7771. Min Act: -0.1700

Data Index: 2357617 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7687. Min Act: -0.1700

Data Index: 5261610 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7462. Min Act: -0.1700

Data Index: 4282125 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7358. Min Act: -0.1698

Data Index: 8217667 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7209. Min Act: -0.1579

Data Index: 8536385 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7298. Min Act: -0.1700

Data Index: 8425276 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7093. Min Act: -0.1688

Data Index: 617704 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7167. Min Act: -0.1669

Data Index: 6271398 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7038. Min Act: -0.1616

Data Index: 6619975 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7043. Min Act: -0.1700

Data Index: 4910149 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7115. Min Act: -0.1700

Data Index: 3332697 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.7015. Min Act: -0.1697

Data Index: 3452713 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6854. Min Act: -0.1700

Data Index: 7239616 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6829. Min Act: -0.1700

Data Index: 3003286 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.8237. Min Range: -1.8237

Max Act: 1.6749. Min Act: -0.1700

Data Index: 1138441 (Open Web Text)

Max Activating Token Index: 61