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

Dataset: Open Web Text

Neuron 233 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: 1.6529. Min Range: -1.6529

Max Act: 1.6529. Min Act: -0.1641

Data Index: 3249333 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5986. Min Act: -0.1477

Data Index: 175460 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5958. Min Act: -0.1107

Data Index: 4488716 (Open Web Text)

Max Activating Token Index: 407

Text #3

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5936. Min Act: -0.0972

Data Index: 8075578 (Open Web Text)

Max Activating Token Index: 445

Text #4

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5648. Min Act: -0.1037

Data Index: 4937049 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5651. Min Act: -0.0611

Data Index: 5645897 (Open Web Text)

Max Activating Token Index: 646

Text #6

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5584. Min Act: -0.0642

Data Index: 4288017 (Open Web Text)

Max Activating Token Index: 899

Text #7

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5576. Min Act: -0.0757

Data Index: 8427152 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5536. Min Act: -0.0616

Data Index: 6126239 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5441. Min Act: -0.1611

Data Index: 3970684 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5400. Min Act: -0.1336

Data Index: 6175973 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5276. Min Act: -0.0644

Data Index: 5640283 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5322. Min Act: -0.0621

Data Index: 175461 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5075. Min Act: -0.1227

Data Index: 2538670 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5057. Min Act: -0.0824

Data Index: 4106285 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5065. Min Act: -0.1411

Data Index: 5260271 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5017. Min Act: -0.1065

Data Index: 6419913 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5047. Min Act: -0.0736

Data Index: 8719172 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5135. Min Act: -0.0779

Data Index: 5750190 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5066. Min Act: -0.1496

Data Index: 8734055 (Open Web Text)

Max Activating Token Index: 297