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

Dataset: Open Web Text

Neuron 155 in Layer 2

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: 8.1718. Min Range: -8.1718

Max Act: 8.1718. Min Act: -0.1700

Data Index: 3676086 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.5622. Min Act: -0.1700

Data Index: 4019295 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.5358. Min Act: -0.1700

Data Index: 2588165 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.4727. Min Act: -0.1700

Data Index: 6370358 (Open Web Text)

Max Activating Token Index: 983

Text #4

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.5217. Min Act: -0.1700

Data Index: 4654596 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.4036. Min Act: -0.1700

Data Index: 1552308 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.4082. Min Act: -0.1700

Data Index: 2585731 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.3676. Min Act: -0.1700

Data Index: 5721150 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.3594. Min Act: -0.1700

Data Index: 750579 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.3100. Min Act: -0.1700

Data Index: 2827100 (Open Web Text)

Max Activating Token Index: 974

Text #10

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.3292. Min Act: -0.1700

Data Index: 7702413 (Open Web Text)

Max Activating Token Index: 235

Text #11

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.3030. Min Act: -0.1700

Data Index: 2519661 (Open Web Text)

Max Activating Token Index: 349

Text #12

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2918. Min Act: -0.1700

Data Index: 5374166 (Open Web Text)

Max Activating Token Index: 621

Text #13

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2529. Min Act: -0.1700

Data Index: 4652178 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.1876. Min Act: -0.1700

Data Index: 2764404 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2242. Min Act: -0.1700

Data Index: 7452237 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2465. Min Act: -0.1700

Data Index: 1825212 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2484. Min Act: -0.1700

Data Index: 4945487 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2434. Min Act: -0.1700

Data Index: 3207053 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 8.1718. Min Range: -8.1718

Max Act: 7.2457. Min Act: -0.1700

Data Index: 2963516 (Open Web Text)

Max Activating Token Index: 341