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

Dataset: Open Web Text

Neuron 1425 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: 3.5735. Min Range: -3.5735

Max Act: 3.5735. Min Act: -0.1700

Data Index: 5306562 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.5636. Min Act: -0.1700

Data Index: 6844862 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.5000. Min Act: -0.1700

Data Index: 8252535 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.5033. Min Act: -0.1700

Data Index: 6793103 (Open Web Text)

Max Activating Token Index: 914

Text #4

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.5003. Min Act: -0.1700

Data Index: 7127884 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4488. Min Act: -0.1700

Data Index: 722636 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4409. Min Act: -0.1700

Data Index: 2655399 (Open Web Text)

Max Activating Token Index: 905

Text #7

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4368. Min Act: -0.1700

Data Index: 7585758 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1877848 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4339. Min Act: -0.1700

Data Index: 7187906 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4165. Min Act: -0.1700

Data Index: 1637925 (Open Web Text)

Max Activating Token Index: 57

Text #11

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4172. Min Act: -0.1700

Data Index: 3981818 (Open Web Text)

Max Activating Token Index: 215

Text #12

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4050. Min Act: -0.1700

Data Index: 3857847 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4192. Min Act: -0.1700

Data Index: 1863711 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4047. Min Act: -0.1700

Data Index: 8227377 (Open Web Text)

Max Activating Token Index: 604

Text #15

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4025. Min Act: -0.1700

Data Index: 6793104 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4182. Min Act: -0.1700

Data Index: 8114183 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4061. Min Act: -0.1700

Data Index: 2371281 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4080. Min Act: -0.1700

Data Index: 6403116 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 3.5735. Min Range: -3.5735

Max Act: 3.4122. Min Act: -0.1700

Data Index: 4858300 (Open Web Text)

Max Activating Token Index: 978