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

Dataset: Open Web Text

Neuron 1703 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: 4.7997. Min Range: -4.7997

Max Act: 4.7997. Min Act: -0.1700

Data Index: 404938 (Open Web Text)

Max Activating Token Index: 478

Text #1

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7383. Min Act: -0.1700

Data Index: 1634392 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7766. Min Act: -0.1700

Data Index: 432415 (Open Web Text)

Max Activating Token Index: 196

Text #3

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7560. Min Act: -0.1700

Data Index: 7823748 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.7291. Min Act: -0.1700

Data Index: 2335454 (Open Web Text)

Max Activating Token Index: 700

Text #5

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6549. Min Act: -0.1700

Data Index: 7450830 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6591. Min Act: -0.1700

Data Index: 2816295 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6226. Min Act: -0.1700

Data Index: 7321915 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6528. Min Act: -0.1700

Data Index: 3794851 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6181. Min Act: -0.1700

Data Index: 7582384 (Open Web Text)

Max Activating Token Index: 185

Text #10

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6146. Min Act: -0.1700

Data Index: 4902977 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6455. Min Act: -0.1700

Data Index: 1325002 (Open Web Text)

Max Activating Token Index: 487

Text #12

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5821. Min Act: -0.1700

Data Index: 749321 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.6235. Min Act: -0.1700

Data Index: 1229627 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5584. Min Act: -0.1700

Data Index: 6278855 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5756. Min Act: -0.1700

Data Index: 760396 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5608. Min Act: -0.1700

Data Index: 5881144 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5288. Min Act: -0.1700

Data Index: 1202016 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5655. Min Act: -0.1700

Data Index: 1625507 (Open Web Text)

Max Activating Token Index: 997

Text #19

Max Range: 4.7997. Min Range: -4.7997

Max Act: 4.5293. Min Act: -0.1700

Data Index: 5673184 (Open Web Text)

Max Activating Token Index: 801