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

Dataset: Open Web Text

Neuron 1317 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: 1.7513. Min Range: -1.7513

Max Act: 1.7513. Min Act: -0.1700

Data Index: 1911919 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.7426. Min Act: -0.1700

Data Index: 193637 (Open Web Text)

Max Activating Token Index: 81

Text #2

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.7125. Min Act: -0.1700

Data Index: 1123982 (Open Web Text)

Max Activating Token Index: 262

Text #3

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.7002. Min Act: -0.1700

Data Index: 6303740 (Open Web Text)

Max Activating Token Index: 871

Text #4

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6887. Min Act: -0.1700

Data Index: 6445772 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6958. Min Act: -0.1700

Data Index: 1844916 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6742. Min Act: -0.1700

Data Index: 8204728 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6723. Min Act: -0.1700

Data Index: 4818077 (Open Web Text)

Max Activating Token Index: 177

Text #8

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6654. Min Act: -0.1700

Data Index: 1584027 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6553. Min Act: -0.1700

Data Index: 3450011 (Open Web Text)

Max Activating Token Index: 823

Text #10

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6534. Min Act: -0.1700

Data Index: 6351072 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6528. Min Act: -0.1700

Data Index: 3071163 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6540. Min Act: -0.1700

Data Index: 8624846 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6563. Min Act: -0.1700

Data Index: 8438114 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6520. Min Act: -0.1700

Data Index: 222930 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6474. Min Act: -0.1700

Data Index: 3057306 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6365. Min Act: -0.1700

Data Index: 8747718 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6288. Min Act: -0.1700

Data Index: 7324892 (Open Web Text)

Max Activating Token Index: 46

Text #18

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6448. Min Act: -0.1700

Data Index: 8594379 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 1.7513. Min Range: -1.7513

Max Act: 1.6271. Min Act: -0.1700

Data Index: 6601415 (Open Web Text)

Max Activating Token Index: 27