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

Dataset: Open Web Text

Neuron 200 in Layer 5

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: 4.4645. Min Range: -4.4645

Max Act: 4.4454. Min Act: -0.1700

Data Index: 2286725 (Open Web Text)

Max Activating Token Index: 979

Text #1

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.4645. Min Act: -0.1700

Data Index: 3522968 (Open Web Text)

Max Activating Token Index: 840

Text #2

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3603. Min Act: -0.1700

Data Index: 2416566 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3849. Min Act: -0.1700

Data Index: 2428336 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3537. Min Act: -0.1700

Data Index: 2524902 (Open Web Text)

Max Activating Token Index: 160

Text #5

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3058. Min Act: -0.1700

Data Index: 2959726 (Open Web Text)

Max Activating Token Index: 881

Text #6

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3209. Min Act: -0.1700

Data Index: 7895059 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3150. Min Act: -0.1700

Data Index: 2370999 (Open Web Text)

Max Activating Token Index: 1002

Text #8

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2979. Min Act: -0.1700

Data Index: 1575758 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3193. Min Act: -0.1700

Data Index: 7607007 (Open Web Text)

Max Activating Token Index: 858

Text #10

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.3062. Min Act: -0.1700

Data Index: 7182171 (Open Web Text)

Max Activating Token Index: 598

Text #11

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2501. Min Act: -0.1700

Data Index: 1371595 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2818. Min Act: -0.1700

Data Index: 1048549 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2234. Min Act: -0.1700

Data Index: 6772181 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2406. Min Act: -0.1700

Data Index: 3010372 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2466. Min Act: -0.1700

Data Index: 2824710 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2446. Min Act: -0.1700

Data Index: 6109048 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2504. Min Act: -0.1700

Data Index: 5795009 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2178. Min Act: -0.1700

Data Index: 3974391 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 4.4645. Min Range: -4.4645

Max Act: 4.2710. Min Act: -0.1700

Data Index: 5450688 (Open Web Text)

Max Activating Token Index: 768