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

Dataset: Open Web Text

Neuron 896 in Layer 6

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: 3.2527. Min Range: -3.2527

Max Act: 3.2527. Min Act: -0.1700

Data Index: 3382769 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.2518. Min Act: -0.1700

Data Index: 7600772 (Open Web Text)

Max Activating Token Index: 740

Text #2

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1710. Min Act: -0.1700

Data Index: 7724965 (Open Web Text)

Max Activating Token Index: 426

Text #3

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1527. Min Act: -0.1700

Data Index: 5887200 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1372. Min Act: -0.1700

Data Index: 3183413 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1221. Min Act: -0.1700

Data Index: 5879792 (Open Web Text)

Max Activating Token Index: 151

Text #6

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1110. Min Act: -0.1700

Data Index: 4193346 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1082. Min Act: -0.1700

Data Index: 2934686 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1046. Min Act: -0.1700

Data Index: 8280371 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1000. Min Act: -0.1700

Data Index: 42714 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0870. Min Act: -0.1700

Data Index: 328315 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0689. Min Act: -0.1700

Data Index: 6425744 (Open Web Text)

Max Activating Token Index: 712

Text #12

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1407147 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0832. Min Act: -0.1700

Data Index: 7305086 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0712. Min Act: -0.1700

Data Index: 6639693 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0639. Min Act: -0.1700

Data Index: 4729384 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0524. Min Act: -0.1700

Data Index: 3728107 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0631. Min Act: -0.1700

Data Index: 5257178 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0548. Min Act: -0.1700

Data Index: 4131989 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.0619. Min Act: -0.1700

Data Index: 1472911 (Open Web Text)

Max Activating Token Index: 119