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

Dataset: Open Web Text

Neuron 2348 in Layer 5

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: 4.0286. Min Range: -4.0286

Max Act: 4.0286. Min Act: -0.1700

Data Index: 1038873 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9888. Min Act: -0.1700

Data Index: 4845611 (Open Web Text)

Max Activating Token Index: 270

Text #2

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9509. Min Act: -0.1700

Data Index: 5964770 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9565. Min Act: -0.1700

Data Index: 5001740 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9543. Min Act: -0.1700

Data Index: 250284 (Open Web Text)

Max Activating Token Index: 223

Text #5

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8714. Min Act: -0.1700

Data Index: 3816146 (Open Web Text)

Max Activating Token Index: 730

Text #6

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9114. Min Act: -0.1700

Data Index: 7340568 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9718. Min Act: -0.1700

Data Index: 6420731 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9517. Min Act: -0.1700

Data Index: 7275056 (Open Web Text)

Max Activating Token Index: 898

Text #9

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9365. Min Act: -0.1700

Data Index: 2888783 (Open Web Text)

Max Activating Token Index: 823

Text #10

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9023. Min Act: -0.1700

Data Index: 7808671 (Open Web Text)

Max Activating Token Index: 955

Text #11

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8511. Min Act: -0.1700

Data Index: 843456 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9065. Min Act: -0.1700

Data Index: 5316136 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8782. Min Act: -0.1700

Data Index: 7201947 (Open Web Text)

Max Activating Token Index: 730

Text #14

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9122. Min Act: -0.1700

Data Index: 4142099 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8837. Min Act: -0.1700

Data Index: 6593657 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8872. Min Act: -0.1700

Data Index: 352055 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.9153. Min Act: -0.1700

Data Index: 3582752 (Open Web Text)

Max Activating Token Index: 248

Text #18

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8513. Min Act: -0.1700

Data Index: 2002424 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 4.0286. Min Range: -4.0286

Max Act: 3.8438. Min Act: -0.1700

Data Index: 3527568 (Open Web Text)

Max Activating Token Index: 894