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

Dataset: Open Web Text

Neuron 2612 in Layer 6

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: 4.7428. Min Range: -4.7428

Max Act: 4.7428. Min Act: -0.1700

Data Index: 1041681 (Open Web Text)

Max Activating Token Index: 753

Text #1

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.3358. Min Act: -0.1700

Data Index: 3136822 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.3371. Min Act: -0.1700

Data Index: 2827840 (Open Web Text)

Max Activating Token Index: 347

Text #3

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2779. Min Act: -0.1700

Data Index: 3879286 (Open Web Text)

Max Activating Token Index: 358

Text #4

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2574. Min Act: -0.1700

Data Index: 2041471 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2357. Min Act: -0.1700

Data Index: 189843 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2183. Min Act: -0.1700

Data Index: 3247891 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2183. Min Act: -0.1700

Data Index: 1693923 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2366. Min Act: -0.1700

Data Index: 1481491 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2183. Min Act: -0.1700

Data Index: 103438 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2183. Min Act: -0.1700

Data Index: 7064913 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.2712. Min Act: -0.1700

Data Index: 5477960 (Open Web Text)

Max Activating Token Index: 886

Text #12

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1649. Min Act: -0.1700

Data Index: 4881575 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1704. Min Act: -0.1700

Data Index: 6216625 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1399. Min Act: -0.1700

Data Index: 7618204 (Open Web Text)

Max Activating Token Index: 857

Text #15

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1836. Min Act: -0.1700

Data Index: 4902117 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1903. Min Act: -0.1700

Data Index: 7983565 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1891. Min Act: -0.1700

Data Index: 1250027 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1528. Min Act: -0.1700

Data Index: 4695447 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 4.7428. Min Range: -4.7428

Max Act: 4.1561. Min Act: -0.1700

Data Index: 752063 (Open Web Text)

Max Activating Token Index: 853