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

Dataset: Open Web Text

Neuron 3060 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: 4.0014. Min Range: -4.0014

Max Act: 4.0014. Min Act: -0.1700

Data Index: 4410459 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.8455. Min Act: -0.1700

Data Index: 4782077 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.8436. Min Act: -0.1700

Data Index: 5866426 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.8247. Min Act: -0.1700

Data Index: 4808799 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.8036. Min Act: -0.1700

Data Index: 2127076 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7561. Min Act: -0.1700

Data Index: 3685235 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7571. Min Act: -0.1700

Data Index: 5159879 (Open Web Text)

Max Activating Token Index: 182

Text #7

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7643. Min Act: -0.1700

Data Index: 473128 (Open Web Text)

Max Activating Token Index: 941

Text #8

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7630. Min Act: -0.1700

Data Index: 6133975 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7238. Min Act: -0.1700

Data Index: 3350078 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7458. Min Act: -0.1700

Data Index: 1443280 (Open Web Text)

Max Activating Token Index: 481

Text #11

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7544. Min Act: -0.1700

Data Index: 447836 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.6926. Min Act: -0.1700

Data Index: 7983193 (Open Web Text)

Max Activating Token Index: 830

Text #13

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7125. Min Act: -0.1700

Data Index: 5169895 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.6979. Min Act: -0.1700

Data Index: 2347946 (Open Web Text)

Max Activating Token Index: 835

Text #15

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.6927. Min Act: -0.1700

Data Index: 4377064 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.7039. Min Act: -0.1700

Data Index: 3214916 (Open Web Text)

Max Activating Token Index: 316

Text #17

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.6689. Min Act: -0.1700

Data Index: 4940152 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.6442. Min Act: -0.1700

Data Index: 429656 (Open Web Text)

Max Activating Token Index: 496

Text #19

Max Range: 4.0014. Min Range: -4.0014

Max Act: 3.6871. Min Act: -0.1700

Data Index: 4690167 (Open Web Text)

Max Activating Token Index: 999