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

Dataset: Open Web Text

Neuron 1828 in Layer 4

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: 4.9792. Min Range: -4.9792

Max Act: 4.9792. Min Act: -0.1700

Data Index: 591071 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.9506. Min Act: -0.1700

Data Index: 3395856 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.9178. Min Act: -0.1700

Data Index: 6366478 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8321. Min Act: -0.1700

Data Index: 7052983 (Open Web Text)

Max Activating Token Index: 1018

Text #4

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8210. Min Act: -0.1700

Data Index: 5850360 (Open Web Text)

Max Activating Token Index: 796

Text #5

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7531. Min Act: -0.1700

Data Index: 7882325 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6888. Min Act: -0.1700

Data Index: 5043383 (Open Web Text)

Max Activating Token Index: 181

Text #7

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7820. Min Act: -0.1700

Data Index: 7850842 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7651. Min Act: -0.1700

Data Index: 84471 (Open Web Text)

Max Activating Token Index: 901

Text #9

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7453. Min Act: -0.1700

Data Index: 4973667 (Open Web Text)

Max Activating Token Index: 344

Text #10

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6899. Min Act: -0.1700

Data Index: 6747508 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7380. Min Act: -0.1700

Data Index: 752811 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6903. Min Act: -0.1700

Data Index: 1680278 (Open Web Text)

Max Activating Token Index: 959

Text #13

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7515. Min Act: -0.1700

Data Index: 4440152 (Open Web Text)

Max Activating Token Index: 35

Text #14

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6951. Min Act: -0.1700

Data Index: 6477073 (Open Web Text)

Max Activating Token Index: 792

Text #15

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7181. Min Act: -0.1700

Data Index: 2229716 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6842. Min Act: -0.1700

Data Index: 1566094 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6914. Min Act: -0.1700

Data Index: 231831 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6996. Min Act: -0.1700

Data Index: 1446325 (Open Web Text)

Max Activating Token Index: 465

Text #19

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.6779. Min Act: -0.1700

Data Index: 2099545 (Open Web Text)

Max Activating Token Index: 692