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

Dataset: Open Web Text

Neuron 2128 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: 5.5832. Min Range: -5.5832

Max Act: 5.5556. Min Act: -0.1700

Data Index: 4638800 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.5832. Min Act: -0.1700

Data Index: 1248143 (Open Web Text)

Max Activating Token Index: 730

Text #2

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.2694. Min Act: -0.1700

Data Index: 7706871 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1013. Min Act: -0.1700

Data Index: 7642251 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1346. Min Act: -0.1700

Data Index: 2082374 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1859. Min Act: -0.1700

Data Index: 89336 (Open Web Text)

Max Activating Token Index: 961

Text #6

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1376. Min Act: -0.1700

Data Index: 587836 (Open Web Text)

Max Activating Token Index: 551

Text #7

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1746. Min Act: -0.1700

Data Index: 6470122 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.2132. Min Act: -0.1700

Data Index: 2886539 (Open Web Text)

Max Activating Token Index: 958

Text #9

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1360. Min Act: -0.1700

Data Index: 2270128 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1798. Min Act: -0.1700

Data Index: 8527366 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.1227. Min Act: -0.1700

Data Index: 6279339 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0686. Min Act: -0.1700

Data Index: 5248480 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0666. Min Act: -0.1700

Data Index: 2399638 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0372. Min Act: -0.1700

Data Index: 4342046 (Open Web Text)

Max Activating Token Index: 583

Text #15

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0207. Min Act: -0.1700

Data Index: 2002177 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0180. Min Act: -0.1700

Data Index: 2176380 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 5.5832. Min Range: -5.5832

Max Act: 4.9062. Min Act: -0.1700

Data Index: 6265347 (Open Web Text)

Max Activating Token Index: 316

Text #18

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0313. Min Act: -0.1700

Data Index: 3318710 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 5.5832. Min Range: -5.5832

Max Act: 5.0296. Min Act: -0.1700

Data Index: 441863 (Open Web Text)

Max Activating Token Index: 347