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

Dataset: Open Web Text

Neuron 3039 in Layer 6

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: 3.5479. Min Range: -3.5479

Max Act: 3.5479. Min Act: -0.0098

Data Index: 796591 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.5291. Min Act: -0.0334

Data Index: 135214 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4872. Min Act: -0.1142

Data Index: 1005894 (Open Web Text)

Max Activating Token Index: 344

Text #3

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.5115. Min Act: -0.0780

Data Index: 7961382 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.5350. Min Act: -0.0552

Data Index: 6546861 (Open Web Text)

Max Activating Token Index: 391

Text #5

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4875. Min Act: -0.1513

Data Index: 4610724 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4740. Min Act: -0.0028

Data Index: 5859708 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4735. Min Act: -0.0881

Data Index: 827443 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4516. Min Act: -0.0619

Data Index: 3069600 (Open Web Text)

Max Activating Token Index: 308

Text #9

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4600. Min Act: -0.1394

Data Index: 1857139 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4268. Min Act: -0.1055

Data Index: 1955748 (Open Web Text)

Max Activating Token Index: 1008

Text #11

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4229. Min Act: -0.1493

Data Index: 5231648 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4206. Min Act: -0.0915

Data Index: 1276646 (Open Web Text)

Max Activating Token Index: 812

Text #13

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.3995. Min Act: -0.1012

Data Index: 3592501 (Open Web Text)

Max Activating Token Index: 399

Text #14

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4113. Min Act: -0.0694

Data Index: 1668157 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4022. Min Act: -0.0842

Data Index: 7831527 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.4125. Min Act: -0.0661

Data Index: 5108259 (Open Web Text)

Max Activating Token Index: 979

Text #17

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.3850. Min Act: -0.0097

Data Index: 6306854 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.3853. Min Act: -0.0686

Data Index: 1812611 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 3.5479. Min Range: -3.5479

Max Act: 3.3624. Min Act: -0.1002

Data Index: 4951493 (Open Web Text)

Max Activating Token Index: 868