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

Dataset: Open Web Text

Neuron 345 in Layer 3

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: 3.4177. Min Range: -3.4177

Max Act: 3.4177. Min Act: -0.1700

Data Index: 4049669 (Open Web Text)

Max Activating Token Index: 848

Text #1

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.3412. Min Act: -0.1700

Data Index: 2374096 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.3277. Min Act: -0.1700

Data Index: 2741099 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1442184 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.3123. Min Act: -0.1700

Data Index: 4506721 (Open Web Text)

Max Activating Token Index: 140

Text #5

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2853. Min Act: -0.1700

Data Index: 1933136 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2928. Min Act: -0.1700

Data Index: 2727203 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2870. Min Act: -0.1700

Data Index: 6753703 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2659. Min Act: -0.1700

Data Index: 6197686 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2779. Min Act: -0.1700

Data Index: 4727089 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2150. Min Act: -0.1700

Data Index: 7066638 (Open Web Text)

Max Activating Token Index: 550

Text #11

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2825. Min Act: -0.1700

Data Index: 6048781 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2386. Min Act: -0.1700

Data Index: 3293531 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2386. Min Act: -0.1700

Data Index: 1603073 (Open Web Text)

Max Activating Token Index: 176

Text #14

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2562. Min Act: -0.1700

Data Index: 7837799 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1547289 (Open Web Text)

Max Activating Token Index: 205

Text #16

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2660. Min Act: -0.1700

Data Index: 6097486 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2073. Min Act: -0.1700

Data Index: 6053636 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2085. Min Act: -0.1700

Data Index: 6963778 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.1650. Min Act: -0.1700

Data Index: 6061920 (Open Web Text)

Max Activating Token Index: 547