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

Dataset: Open Web Text

Neuron 390 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: 3.9549. Min Range: -3.9549

Max Act: 3.9549. Min Act: -0.1700

Data Index: 6422037 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8992. Min Act: -0.1700

Data Index: 1036631 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8695. Min Act: -0.1700

Data Index: 4568590 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8299. Min Act: -0.1700

Data Index: 7083326 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8189. Min Act: -0.1700

Data Index: 7729947 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8091. Min Act: -0.1700

Data Index: 6548093 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8035. Min Act: -0.1700

Data Index: 6506301 (Open Web Text)

Max Activating Token Index: 163

Text #7

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.8009. Min Act: -0.1700

Data Index: 8196870 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7805. Min Act: -0.1700

Data Index: 730020 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7798. Min Act: -0.1700

Data Index: 1907296 (Open Web Text)

Max Activating Token Index: 187

Text #10

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7586. Min Act: -0.1700

Data Index: 3982196 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7761. Min Act: -0.1700

Data Index: 4624457 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7698. Min Act: -0.1700

Data Index: 255572 (Open Web Text)

Max Activating Token Index: 120

Text #13

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7763. Min Act: -0.1700

Data Index: 5458102 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7688. Min Act: -0.1700

Data Index: 2363372 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7728. Min Act: -0.1700

Data Index: 7437648 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7682. Min Act: -0.1700

Data Index: 6312401 (Open Web Text)

Max Activating Token Index: 156

Text #17

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7661. Min Act: -0.1700

Data Index: 2343840 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7739. Min Act: -0.1700

Data Index: 791875 (Open Web Text)

Max Activating Token Index: 736

Text #19

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.7551. Min Act: -0.1700

Data Index: 2838625 (Open Web Text)

Max Activating Token Index: 996