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

Dataset: Open Web Text

Neuron 1396 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: 4.6720. Min Range: -4.6720

Max Act: 4.6720. Min Act: -0.1700

Data Index: 1341839 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3757. Min Act: -0.1700

Data Index: 2194560 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3460. Min Act: -0.1700

Data Index: 84885 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3589. Min Act: -0.1700

Data Index: 4749067 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3501. Min Act: -0.1700

Data Index: 5661608 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3313. Min Act: -0.1700

Data Index: 1614844 (Open Web Text)

Max Activating Token Index: 340

Text #6

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3256. Min Act: -0.1700

Data Index: 5067449 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3400. Min Act: -0.1700

Data Index: 6598617 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.3291. Min Act: -0.1700

Data Index: 7032420 (Open Web Text)

Max Activating Token Index: 840

Text #9

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2571. Min Act: -0.1700

Data Index: 3856461 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2528. Min Act: -0.1700

Data Index: 5719007 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2643. Min Act: -0.1700

Data Index: 8831802 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2387. Min Act: -0.1700

Data Index: 5561530 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2590. Min Act: -0.1700

Data Index: 6472852 (Open Web Text)

Max Activating Token Index: 331

Text #14

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2384. Min Act: -0.1700

Data Index: 7067677 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2353. Min Act: -0.1700

Data Index: 4072764 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2428. Min Act: -0.1700

Data Index: 2434375 (Open Web Text)

Max Activating Token Index: 758

Text #17

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.1991. Min Act: -0.1700

Data Index: 2094805 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2125. Min Act: -0.1700

Data Index: 5284450 (Open Web Text)

Max Activating Token Index: 846

Text #19

Max Range: 4.6720. Min Range: -4.6720

Max Act: 4.2532. Min Act: -0.1700

Data Index: 3505380 (Open Web Text)

Max Activating Token Index: 819