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

Dataset: Open Web Text

Neuron 2428 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: 4.3668. Min Range: -4.3668

Max Act: 4.3668. Min Act: -0.1700

Data Index: 3717775 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 4.3668. Min Range: -4.3668

Max Act: 4.1852. Min Act: -0.1700

Data Index: 3776939 (Open Web Text)

Max Activating Token Index: 616

Text #2

Max Range: 4.3668. Min Range: -4.3668

Max Act: 4.0308. Min Act: -0.1700

Data Index: 4929309 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 4.3668. Min Range: -4.3668

Max Act: 4.0130. Min Act: -0.1700

Data Index: 7651002 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 4.3668. Min Range: -4.3668

Max Act: 4.0847. Min Act: -0.1700

Data Index: 7473864 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 4.3668. Min Range: -4.3668

Max Act: 4.0025. Min Act: -0.1700

Data Index: 862219 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.9237. Min Act: -0.1700

Data Index: 2155763 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.9087. Min Act: -0.1700

Data Index: 7224345 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.8981. Min Act: -0.1700

Data Index: 205278 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.8508. Min Act: -0.1700

Data Index: 6847702 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.8655. Min Act: -0.1700

Data Index: 302041 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7937. Min Act: -0.1700

Data Index: 2002311 (Open Web Text)

Max Activating Token Index: 998

Text #12

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7710. Min Act: -0.1700

Data Index: 7289055 (Open Web Text)

Max Activating Token Index: 745

Text #13

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7615. Min Act: -0.1700

Data Index: 8273652 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7424. Min Act: -0.1700

Data Index: 3162525 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.8178. Min Act: -0.1700

Data Index: 6307583 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7685. Min Act: -0.1700

Data Index: 7949343 (Open Web Text)

Max Activating Token Index: 481

Text #17

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7130. Min Act: -0.1700

Data Index: 4583658 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.7169. Min Act: -0.1700

Data Index: 1109502 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 4.3668. Min Range: -4.3668

Max Act: 3.6862. Min Act: -0.1700

Data Index: 1938862 (Open Web Text)

Max Activating Token Index: 358