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

Dataset: Open Web Text

Neuron 1064 in Layer 0

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: 1.3925. Min Range: -1.3925

Max Act: 1.3925. Min Act: -0.1700

Data Index: 8513684 (Open Web Text)

Max Activating Token Index: 554

Text #1

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3710. Min Act: -0.1700

Data Index: 1841687 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3488. Min Act: -0.1700

Data Index: 1146946 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3492. Min Act: -0.1698

Data Index: 2738557 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3278. Min Act: -0.1700

Data Index: 7133648 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3266. Min Act: -0.1700

Data Index: 837552 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3284. Min Act: -0.1700

Data Index: 3341865 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3342. Min Act: -0.1700

Data Index: 7059619 (Open Web Text)

Max Activating Token Index: 755

Text #8

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3176. Min Act: -0.1700

Data Index: 6168851 (Open Web Text)

Max Activating Token Index: 838

Text #9

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3195. Min Act: -0.1700

Data Index: 2263294 (Open Web Text)

Max Activating Token Index: 496

Text #10

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3199. Min Act: -0.1700

Data Index: 198569 (Open Web Text)

Max Activating Token Index: 227

Text #11

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3221. Min Act: -0.1700

Data Index: 1278467 (Open Web Text)

Max Activating Token Index: 883

Text #12

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3047. Min Act: -0.1700

Data Index: 2738558 (Open Web Text)

Max Activating Token Index: 437

Text #13

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3022. Min Act: -0.1619

Data Index: 1787751 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3045. Min Act: -0.1517

Data Index: 3366766 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3060. Min Act: -0.1700

Data Index: 1793137 (Open Web Text)

Max Activating Token Index: 929

Text #16

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.3024. Min Act: -0.1700

Data Index: 3381980 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2927. Min Act: -0.1700

Data Index: 1333284 (Open Web Text)

Max Activating Token Index: 622

Text #18

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2941. Min Act: -0.1700

Data Index: 5114523 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 1.3925. Min Range: -1.3925

Max Act: 1.2951. Min Act: -0.1700

Data Index: 3366767 (Open Web Text)

Max Activating Token Index: 364