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

Dataset: Open Web Text

Neuron 33 in Layer 0

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: 3.1737. Min Range: -3.1737

Max Act: 3.1737. Min Act: -0.1700

Data Index: 8334062 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0931. Min Act: -0.1700

Data Index: 429441 (Open Web Text)

Max Activating Token Index: 898

Text #2

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0847. Min Act: -0.1700

Data Index: 6249622 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0694. Min Act: -0.1700

Data Index: 8025866 (Open Web Text)

Max Activating Token Index: 48

Text #4

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0494. Min Act: -0.1700

Data Index: 7753377 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0534. Min Act: -0.1700

Data Index: 3341916 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 3.1737. Min Range: -3.1737

Max Act: 3.0042. Min Act: -0.1700

Data Index: 3571630 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9991. Min Act: -0.1700

Data Index: 4194911 (Open Web Text)

Max Activating Token Index: 278

Text #8

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9731. Min Act: -0.1700

Data Index: 3173448 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9803. Min Act: -0.1700

Data Index: 491586 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9843. Min Act: -0.1700

Data Index: 6568231 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9826. Min Act: -0.1700

Data Index: 4489895 (Open Web Text)

Max Activating Token Index: 735

Text #12

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9784. Min Act: -0.1700

Data Index: 3175452 (Open Web Text)

Max Activating Token Index: 669

Text #13

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9572. Min Act: -0.1700

Data Index: 587092 (Open Web Text)

Max Activating Token Index: 777

Text #14

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9689. Min Act: -0.1700

Data Index: 6986284 (Open Web Text)

Max Activating Token Index: 935

Text #15

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9618. Min Act: -0.1700

Data Index: 1464141 (Open Web Text)

Max Activating Token Index: 357

Text #16

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9568. Min Act: -0.1700

Data Index: 7112976 (Open Web Text)

Max Activating Token Index: 962

Text #17

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9591. Min Act: -0.1700

Data Index: 3031761 (Open Web Text)

Max Activating Token Index: 900

Text #18

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9613. Min Act: -0.1700

Data Index: 4519350 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 3.1737. Min Range: -3.1737

Max Act: 2.9677. Min Act: -0.1700

Data Index: 5035620 (Open Web Text)

Max Activating Token Index: 928