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

Dataset: Open Web Text

Neuron 1499 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: 7.0191. Min Range: -7.0191

Max Act: 7.0191. Min Act: -0.1700

Data Index: 5728813 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.9336. Min Act: -0.1700

Data Index: 4368710 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.8793. Min Act: -0.1700

Data Index: 7723630 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.8419. Min Act: -0.1700

Data Index: 8128823 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.8274. Min Act: -0.1700

Data Index: 2903171 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7875. Min Act: -0.1700

Data Index: 464138 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.8439. Min Act: -0.1700

Data Index: 8463012 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.8242. Min Act: -0.1700

Data Index: 4657116 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7845. Min Act: -0.1700

Data Index: 1247033 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.8090. Min Act: -0.1700

Data Index: 100848 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7666. Min Act: -0.1700

Data Index: 5953962 (Open Web Text)

Max Activating Token Index: 24

Text #11

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7706. Min Act: -0.1700

Data Index: 7442713 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7849. Min Act: -0.1700

Data Index: 7613719 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7706. Min Act: -0.1700

Data Index: 8694960 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7274. Min Act: -0.1700

Data Index: 8664329 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7406. Min Act: -0.1700

Data Index: 7266877 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7695. Min Act: -0.1700

Data Index: 7448215 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7302. Min Act: -0.1700

Data Index: 6301003 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7410. Min Act: -0.1700

Data Index: 4310870 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 7.0191. Min Range: -7.0191

Max Act: 6.7551. Min Act: -0.1700

Data Index: 1932118 (Open Web Text)

Max Activating Token Index: 52