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

Dataset: Open Web Text

Neuron 283 in Layer 5

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: 3.3320. Min Range: -3.3320

Max Act: 3.3320. Min Act: -0.1700

Data Index: 5939576 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.3087. Min Act: -0.1700

Data Index: 640464 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.3010. Min Act: -0.1700

Data Index: 6642998 (Open Web Text)

Max Activating Token Index: 918

Text #3

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2908. Min Act: -0.1700

Data Index: 5472531 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2699. Min Act: -0.1700

Data Index: 8702345 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2477. Min Act: -0.1700

Data Index: 2887695 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2539. Min Act: -0.1700

Data Index: 8707370 (Open Web Text)

Max Activating Token Index: 534

Text #7

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2724. Min Act: -0.1700

Data Index: 1916302 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2454. Min Act: -0.1700

Data Index: 7109152 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2244. Min Act: -0.1700

Data Index: 8757505 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2124. Min Act: -0.1700

Data Index: 8676194 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2314. Min Act: -0.1700

Data Index: 4678674 (Open Web Text)

Max Activating Token Index: 419

Text #12

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1978. Min Act: -0.1700

Data Index: 935021 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.2043. Min Act: -0.1700

Data Index: 3827373 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1881. Min Act: -0.1700

Data Index: 4730132 (Open Web Text)

Max Activating Token Index: 436

Text #15

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1843. Min Act: -0.1700

Data Index: 226082 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1852. Min Act: -0.1700

Data Index: 4523914 (Open Web Text)

Max Activating Token Index: 836

Text #17

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1839. Min Act: -0.1700

Data Index: 3323722 (Open Web Text)

Max Activating Token Index: 786

Text #18

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1954. Min Act: -0.1700

Data Index: 1446973 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 3.3320. Min Range: -3.3320

Max Act: 3.1947. Min Act: -0.1700

Data Index: 3180243 (Open Web Text)

Max Activating Token Index: 516