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

Dataset: Open Web Text

Neuron 1001 in Layer 2

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: 3.8853. Min Range: -3.8853

Max Act: 3.8853. Min Act: -0.1700

Data Index: 858466 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8784. Min Act: -0.1700

Data Index: 118682 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8428. Min Act: -0.1700

Data Index: 2013607 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8362. Min Act: -0.1700

Data Index: 879478 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8377. Min Act: -0.1700

Data Index: 3156676 (Open Web Text)

Max Activating Token Index: 845

Text #5

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8000. Min Act: -0.1700

Data Index: 2054817 (Open Web Text)

Max Activating Token Index: 229

Text #6

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7990. Min Act: -0.1700

Data Index: 7960748 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7771. Min Act: -0.1700

Data Index: 4105849 (Open Web Text)

Max Activating Token Index: 790

Text #8

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7827. Min Act: -0.1700

Data Index: 5865193 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8003. Min Act: -0.1700

Data Index: 5883807 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7878. Min Act: -0.1700

Data Index: 8478357 (Open Web Text)

Max Activating Token Index: 493

Text #11

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7912. Min Act: -0.1700

Data Index: 6364975 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7565. Min Act: -0.1700

Data Index: 5551937 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7599. Min Act: -0.1700

Data Index: 7930271 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7290. Min Act: -0.1700

Data Index: 3887896 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7835. Min Act: -0.1700

Data Index: 6265554 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7310. Min Act: -0.1700

Data Index: 5941854 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7814. Min Act: -0.1700

Data Index: 5839501 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7337. Min Act: -0.1700

Data Index: 1598159 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7037. Min Act: -0.1700

Data Index: 5071136 (Open Web Text)

Max Activating Token Index: 240