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

Dataset: Open Web Text

Neuron 1503 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: 1.4912. Min Range: -1.4912

Max Act: 1.4912. Min Act: -0.1677

Data Index: 6099355 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4814. Min Act: -0.1696

Data Index: 3085527 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4614. Min Act: -0.1678

Data Index: 7127348 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4683. Min Act: -0.1694

Data Index: 4761833 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4630. Min Act: -0.1700

Data Index: 3416510 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4492. Min Act: -0.1698

Data Index: 6399924 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4413. Min Act: -0.1698

Data Index: 3854693 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4483. Min Act: -0.1632

Data Index: 4542539 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4580. Min Act: -0.1700

Data Index: 75933 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4354. Min Act: -0.1680

Data Index: 5504284 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4414. Min Act: -0.1695

Data Index: 3319278 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4383. Min Act: -0.1700

Data Index: 8506253 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4290. Min Act: -0.1699

Data Index: 1565107 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4371. Min Act: -0.1663

Data Index: 7507082 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4379. Min Act: -0.1700

Data Index: 4273492 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4355. Min Act: -0.1698

Data Index: 1261787 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4374. Min Act: -0.1603

Data Index: 7370168 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4218. Min Act: -0.1700

Data Index: 4384982 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4255. Min Act: -0.1694

Data Index: 3419136 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 1.4912. Min Range: -1.4912

Max Act: 1.4288. Min Act: -0.1700

Data Index: 1997041 (Open Web Text)

Max Activating Token Index: 1022