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

Dataset: Open Web Text

Neuron 548 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: 7.0828. Min Range: -7.0828

Max Act: 7.0187. Min Act: -0.1700

Data Index: 218816 (Open Web Text)

Max Activating Token Index: 852

Text #1

Max Range: 7.0828. Min Range: -7.0828

Max Act: 7.0828. Min Act: -0.1700

Data Index: 8509157 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8816. Min Act: -0.1700

Data Index: 910460 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8429. Min Act: -0.1700

Data Index: 1461565 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8803. Min Act: -0.1700

Data Index: 4517084 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8538. Min Act: -0.1700

Data Index: 6501505 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8359. Min Act: -0.1700

Data Index: 4740618 (Open Web Text)

Max Activating Token Index: 825

Text #7

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8520. Min Act: -0.1700

Data Index: 3669367 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8745. Min Act: -0.1700

Data Index: 4685767 (Open Web Text)

Max Activating Token Index: 221

Text #9

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8954. Min Act: -0.1700

Data Index: 5007794 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8224. Min Act: -0.1700

Data Index: 1930874 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8414. Min Act: -0.1700

Data Index: 4221693 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8195. Min Act: -0.1700

Data Index: 511816 (Open Web Text)

Max Activating Token Index: 237

Text #13

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8011. Min Act: -0.1700

Data Index: 764527 (Open Web Text)

Max Activating Token Index: 273

Text #14

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8693. Min Act: -0.1700

Data Index: 6991811 (Open Web Text)

Max Activating Token Index: 1012

Text #15

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.7864. Min Act: -0.1700

Data Index: 5470505 (Open Web Text)

Max Activating Token Index: 416

Text #16

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8406. Min Act: -0.1700

Data Index: 4272810 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8202. Min Act: -0.1700

Data Index: 2981342 (Open Web Text)

Max Activating Token Index: 175

Text #18

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.8479. Min Act: -0.1698

Data Index: 2193688 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 7.0828. Min Range: -7.0828

Max Act: 6.7235. Min Act: -0.1700

Data Index: 2758946 (Open Web Text)

Max Activating Token Index: 391