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

Dataset: Open Web Text

Neuron 2819 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: 3.4779. Min Range: -3.4779

Max Act: 3.4779. Min Act: -0.1700

Data Index: 393580 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.4194. Min Act: -0.1700

Data Index: 8067724 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.3876. Min Act: -0.1700

Data Index: 6077967 (Open Web Text)

Max Activating Token Index: 914

Text #3

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.3797. Min Act: -0.1700

Data Index: 5218429 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.3362. Min Act: -0.1700

Data Index: 6510781 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.3334. Min Act: -0.1700

Data Index: 1447688 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2265. Min Act: -0.1700

Data Index: 7745106 (Open Web Text)

Max Activating Token Index: 795

Text #7

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2837. Min Act: -0.1700

Data Index: 822162 (Open Web Text)

Max Activating Token Index: 167

Text #8

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2401. Min Act: -0.1700

Data Index: 395162 (Open Web Text)

Max Activating Token Index: 777

Text #9

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2413. Min Act: -0.1700

Data Index: 1809344 (Open Web Text)

Max Activating Token Index: 718

Text #10

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2365. Min Act: -0.1700

Data Index: 8004591 (Open Web Text)

Max Activating Token Index: 739

Text #11

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2098. Min Act: -0.1700

Data Index: 6613565 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.2205. Min Act: -0.1700

Data Index: 8538155 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1948. Min Act: -0.1700

Data Index: 7942340 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1928. Min Act: -0.1700

Data Index: 7244527 (Open Web Text)

Max Activating Token Index: 600

Text #15

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1793. Min Act: -0.1700

Data Index: 8486034 (Open Web Text)

Max Activating Token Index: 912

Text #16

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1907. Min Act: -0.1700

Data Index: 8344780 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1982. Min Act: -0.1700

Data Index: 6952683 (Open Web Text)

Max Activating Token Index: 116

Text #18

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1602. Min Act: -0.1700

Data Index: 7151437 (Open Web Text)

Max Activating Token Index: 219

Text #19

Max Range: 3.4779. Min Range: -3.4779

Max Act: 3.1781. Min Act: -0.1700

Data Index: 3074597 (Open Web Text)

Max Activating Token Index: 930