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

Dataset: Open Web Text

Neuron 970 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: 3.2023. Min Range: -3.2023

Max Act: 3.2023. Min Act: -0.1700

Data Index: 7374230 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1643. Min Act: -0.1700

Data Index: 966314 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1539. Min Act: -0.1700

Data Index: 5140502 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1188. Min Act: -0.1700

Data Index: 5496031 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1231. Min Act: -0.1700

Data Index: 8374682 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1250. Min Act: -0.1700

Data Index: 3384055 (Open Web Text)

Max Activating Token Index: 564

Text #6

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1020884 (Open Web Text)

Max Activating Token Index: 460

Text #7

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1177. Min Act: -0.1700

Data Index: 6471825 (Open Web Text)

Max Activating Token Index: 916

Text #8

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0882. Min Act: -0.1700

Data Index: 1648026 (Open Web Text)

Max Activating Token Index: 893

Text #9

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0913. Min Act: -0.1700

Data Index: 3023303 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1797004 (Open Web Text)

Max Activating Token Index: 241

Text #11

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1060. Min Act: -0.1700

Data Index: 7797635 (Open Web Text)

Max Activating Token Index: 840

Text #12

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0833. Min Act: -0.1700

Data Index: 29994 (Open Web Text)

Max Activating Token Index: 230

Text #13

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0704. Min Act: -0.1700

Data Index: 7556388 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0892. Min Act: -0.1700

Data Index: 8303438 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0980. Min Act: -0.1700

Data Index: 367847 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0405. Min Act: -0.1700

Data Index: 5103021 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0616. Min Act: -0.1700

Data Index: 2374083 (Open Web Text)

Max Activating Token Index: 38

Text #18

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.0564. Min Act: -0.1700

Data Index: 5467589 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 3.2023. Min Range: -3.2023

Max Act: 3.1028. Min Act: -0.1700

Data Index: 6226176 (Open Web Text)

Max Activating Token Index: 831