Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3883 in Layer 25

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.6217. Min Act: -0.1700

Data Index: 7641498 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.3404. Min Act: -0.1700

Data Index: 8008015 (Open Web Text)

Max Activating Token Index: 508

Text #2

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.2779. Min Act: -0.1700

Data Index: 5564571 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.2467. Min Act: -0.1700

Data Index: 4168014 (Open Web Text)

Max Activating Token Index: 337

Text #4

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.1217. Min Act: -0.1700

Data Index: 5952077 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.1529. Min Act: -0.1700

Data Index: 7809645 (Open Web Text)

Max Activating Token Index: 754

Text #6

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0904. Min Act: -0.1700

Data Index: 1017544 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0904. Min Act: -0.1700

Data Index: 1267051 (Open Web Text)

Max Activating Token Index: 725

Text #8

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.1217. Min Act: -0.1700

Data Index: 3422384 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0592. Min Act: -0.1700

Data Index: 4153903 (Open Web Text)

Max Activating Token Index: 182

Text #10

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0279. Min Act: -0.1700

Data Index: 622521 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0279. Min Act: -0.1700

Data Index: 6941169 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 7.6217. Min Range: -7.6217

Max Act: 6.9967. Min Act: -0.1700

Data Index: 4017192 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 7.6217. Min Range: -7.6217

Max Act: 6.9967. Min Act: -0.1700

Data Index: 2367208 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0279. Min Act: -0.1700

Data Index: 4489265 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 7.6217. Min Range: -7.6217

Max Act: 7.0279. Min Act: -0.1700

Data Index: 306313 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 7.6217. Min Range: -7.6217

Max Act: 6.9654. Min Act: -0.1700

Data Index: 3688837 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 7.6217. Min Range: -7.6217

Max Act: 6.9654. Min Act: -0.1700

Data Index: 2161504 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 7.6217. Min Range: -7.6217

Max Act: 6.8717. Min Act: -0.1700

Data Index: 7012409 (Open Web Text)

Max Activating Token Index: 980

Text #19

Max Range: 7.6217. Min Range: -7.6217

Max Act: 6.8092. Min Act: -0.1700

Data Index: 440350 (Open Web Text)

Max Activating Token Index: 938