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

Dataset: Open Web Text

Neuron 2468 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: 4.4822. Min Range: -4.4822

Max Act: 4.4822. Min Act: -0.1700

Data Index: 6614327 (Open Web Text)

Max Activating Token Index: 226

Text #1

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2827. Min Act: -0.1700

Data Index: 5986237 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2671. Min Act: -0.1700

Data Index: 2093158 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2239. Min Act: -0.1700

Data Index: 8792570 (Open Web Text)

Max Activating Token Index: 935

Text #4

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2413. Min Act: -0.1700

Data Index: 5024428 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2674. Min Act: -0.1700

Data Index: 6204786 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2219. Min Act: -0.1700

Data Index: 7390638 (Open Web Text)

Max Activating Token Index: 89

Text #7

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1995. Min Act: -0.1700

Data Index: 6204790 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1894. Min Act: -0.1700

Data Index: 2937125 (Open Web Text)

Max Activating Token Index: 546

Text #9

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.2538. Min Act: -0.1700

Data Index: 4554549 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1722. Min Act: -0.1700

Data Index: 7353510 (Open Web Text)

Max Activating Token Index: 479

Text #11

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1974. Min Act: -0.1700

Data Index: 258880 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1494. Min Act: -0.1700

Data Index: 1870433 (Open Web Text)

Max Activating Token Index: 871

Text #13

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1557. Min Act: -0.1700

Data Index: 6108482 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1704. Min Act: -0.1700

Data Index: 2541677 (Open Web Text)

Max Activating Token Index: 279

Text #15

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1365. Min Act: -0.1700

Data Index: 4379135 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1733. Min Act: -0.1700

Data Index: 3356931 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1461. Min Act: -0.1700

Data Index: 8539856 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.0901. Min Act: -0.1700

Data Index: 5097586 (Open Web Text)

Max Activating Token Index: 811

Text #19

Max Range: 4.4822. Min Range: -4.4822

Max Act: 4.1157. Min Act: -0.1700

Data Index: 2577773 (Open Web Text)

Max Activating Token Index: 909