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

Dataset: Open Web Text

Neuron 82 in Layer 3

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: 4.0754. Min Range: -4.0754

Max Act: 4.0754. Min Act: -0.1700

Data Index: 1149696 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 4.0754. Min Range: -4.0754

Max Act: 4.0592. Min Act: -0.1700

Data Index: 2287365 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 4.0754. Min Range: -4.0754

Max Act: 4.0558. Min Act: -0.1700

Data Index: 3908895 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9887. Min Act: -0.1700

Data Index: 857291 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9851. Min Act: -0.1700

Data Index: 6936608 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 4.0754. Min Range: -4.0754

Max Act: 4.0000. Min Act: -0.1700

Data Index: 6824128 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 4.0754. Min Range: -4.0754

Max Act: 4.0189. Min Act: -0.1700

Data Index: 1862297 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9861. Min Act: -0.1700

Data Index: 6121219 (Open Web Text)

Max Activating Token Index: 232

Text #8

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9751. Min Act: -0.1700

Data Index: 2089153 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9647. Min Act: -0.1700

Data Index: 5155841 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9543. Min Act: -0.1700

Data Index: 459839 (Open Web Text)

Max Activating Token Index: 456

Text #11

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9617. Min Act: -0.1700

Data Index: 437487 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9731. Min Act: -0.1700

Data Index: 4530029 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9744. Min Act: -0.1700

Data Index: 2714976 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9723. Min Act: -0.1700

Data Index: 8662173 (Open Web Text)

Max Activating Token Index: 995

Text #15

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9319. Min Act: -0.1700

Data Index: 1835114 (Open Web Text)

Max Activating Token Index: 475

Text #16

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9309. Min Act: -0.1700

Data Index: 360706 (Open Web Text)

Max Activating Token Index: 978

Text #17

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9268. Min Act: -0.1700

Data Index: 480391 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9648. Min Act: -0.1700

Data Index: 6417883 (Open Web Text)

Max Activating Token Index: 278

Text #19

Max Range: 4.0754. Min Range: -4.0754

Max Act: 3.9435. Min Act: -0.1700

Data Index: 1288739 (Open Web Text)

Max Activating Token Index: 249