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

Dataset: Open Web Text

Neuron 772 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: 5.3989. Min Range: -5.3989

Max Act: 5.3989. Min Act: -0.1700

Data Index: 2926391 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 5.3989. Min Range: -5.3989

Max Act: 5.1082. Min Act: -0.1700

Data Index: 5626900 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.9871. Min Act: -0.1700

Data Index: 8586901 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 5.3989. Min Range: -5.3989

Max Act: 5.0024. Min Act: -0.1700

Data Index: 8188242 (Open Web Text)

Max Activating Token Index: 683

Text #4

Max Range: 5.3989. Min Range: -5.3989

Max Act: 5.0072. Min Act: -0.1700

Data Index: 643462 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.9962. Min Act: -0.1700

Data Index: 8702155 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.9659. Min Act: -0.1700

Data Index: 3683387 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.9250. Min Act: -0.1700

Data Index: 3263972 (Open Web Text)

Max Activating Token Index: 666

Text #8

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8832. Min Act: -0.1700

Data Index: 7687931 (Open Web Text)

Max Activating Token Index: 298

Text #9

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.9117. Min Act: -0.1700

Data Index: 5345349 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8929. Min Act: -0.1700

Data Index: 2530133 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8724. Min Act: -0.1700

Data Index: 3386403 (Open Web Text)

Max Activating Token Index: 680

Text #12

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8716. Min Act: -0.1700

Data Index: 8282623 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.7659. Min Act: -0.1700

Data Index: 7194124 (Open Web Text)

Max Activating Token Index: 896

Text #14

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8028. Min Act: -0.1700

Data Index: 1125144 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8196. Min Act: -0.1700

Data Index: 8403266 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.7859. Min Act: -0.1700

Data Index: 3028679 (Open Web Text)

Max Activating Token Index: 589

Text #17

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.8137. Min Act: -0.1700

Data Index: 5543754 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.7471. Min Act: -0.1700

Data Index: 4447428 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 5.3989. Min Range: -5.3989

Max Act: 4.7737. Min Act: -0.1700

Data Index: 2541557 (Open Web Text)

Max Activating Token Index: 417