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

Dataset: Open Web Text

Neuron 2010 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: 5.3729. Min Range: -5.3729

Max Act: 5.3477. Min Act: -0.1700

Data Index: 8667288 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.3729. Min Act: -0.1700

Data Index: 110909 (Open Web Text)

Max Activating Token Index: 922

Text #2

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.3152. Min Act: -0.1700

Data Index: 7780506 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.2970. Min Act: -0.1700

Data Index: 2405482 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.2522. Min Act: -0.1700

Data Index: 1492437 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1809. Min Act: -0.1700

Data Index: 4857862 (Open Web Text)

Max Activating Token Index: 328

Text #6

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1973. Min Act: -0.1700

Data Index: 6890769 (Open Web Text)

Max Activating Token Index: 405

Text #7

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1685. Min Act: -0.1700

Data Index: 2474761 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1536. Min Act: -0.1700

Data Index: 395173 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1664. Min Act: -0.1700

Data Index: 6285993 (Open Web Text)

Max Activating Token Index: 94

Text #10

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1003. Min Act: -0.1700

Data Index: 2709660 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1080. Min Act: -0.1700

Data Index: 4524089 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1387. Min Act: -0.1700

Data Index: 6560120 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1049. Min Act: -0.1700

Data Index: 4250038 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1318. Min Act: -0.1700

Data Index: 8714187 (Open Web Text)

Max Activating Token Index: 896

Text #15

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.0858. Min Act: -0.1700

Data Index: 6822366 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.0972. Min Act: -0.1700

Data Index: 6457334 (Open Web Text)

Max Activating Token Index: 119

Text #17

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1222. Min Act: -0.1700

Data Index: 5531269 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.1087. Min Act: -0.1700

Data Index: 2424163 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 5.3729. Min Range: -5.3729

Max Act: 5.0672. Min Act: -0.1700

Data Index: 727296 (Open Web Text)

Max Activating Token Index: 793