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

Dataset: Open Web Text

Neuron 6 in Layer 2

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: 3.6528. Min Range: -3.6528

Max Act: 3.6528. Min Act: -0.1700

Data Index: 2748410 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.5831. Min Act: -0.1700

Data Index: 3531724 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.5735. Min Act: -0.1700

Data Index: 6842711 (Open Web Text)

Max Activating Token Index: 225

Text #3

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.5289. Min Act: -0.1700

Data Index: 8832312 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4938. Min Act: -0.1700

Data Index: 2761426 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.5052. Min Act: -0.1700

Data Index: 6842710 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4971. Min Act: -0.1700

Data Index: 6140321 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.5046. Min Act: -0.1700

Data Index: 1551912 (Open Web Text)

Max Activating Token Index: 462

Text #8

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.5001. Min Act: -0.1700

Data Index: 5511725 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4435. Min Act: -0.1700

Data Index: 6849344 (Open Web Text)

Max Activating Token Index: 725

Text #10

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4165. Min Act: -0.1700

Data Index: 6672928 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4483. Min Act: -0.1700

Data Index: 1176575 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4278. Min Act: -0.1700

Data Index: 3201271 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4227. Min Act: -0.1700

Data Index: 3192457 (Open Web Text)

Max Activating Token Index: 307

Text #14

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4118. Min Act: -0.1700

Data Index: 1530806 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4035. Min Act: -0.1700

Data Index: 4781285 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3890. Min Act: -0.1700

Data Index: 8463860 (Open Web Text)

Max Activating Token Index: 1001

Text #17

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3683. Min Act: -0.1700

Data Index: 4930242 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3772. Min Act: -0.1700

Data Index: 3723301 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3568. Min Act: -0.1700

Data Index: 4185355 (Open Web Text)

Max Activating Token Index: 550