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

Dataset: Open Web Text

Neuron 341 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: 4.2040. Min Range: -4.2040

Max Act: 4.1849. Min Act: -0.1700

Data Index: 1328891 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.2040. Min Act: -0.1700

Data Index: 8137516 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1778. Min Act: -0.1700

Data Index: 3100487 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1437. Min Act: -0.1700

Data Index: 1103421 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1859. Min Act: -0.1700

Data Index: 4617084 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0835. Min Act: -0.1700

Data Index: 8249110 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0796. Min Act: -0.1700

Data Index: 8143747 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1466. Min Act: -0.1700

Data Index: 5459564 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1214. Min Act: -0.1700

Data Index: 2241527 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0921. Min Act: -0.1700

Data Index: 6013219 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0591. Min Act: -0.1700

Data Index: 3087848 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0083. Min Act: -0.1700

Data Index: 5142201 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1386. Min Act: -0.1700

Data Index: 2476982 (Open Web Text)

Max Activating Token Index: 392

Text #13

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1041. Min Act: -0.1700

Data Index: 5249016 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0863. Min Act: -0.1700

Data Index: 6573462 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0922. Min Act: -0.1700

Data Index: 8426736 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0142. Min Act: -0.1700

Data Index: 2624010 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0079. Min Act: -0.1700

Data Index: 1319917 (Open Web Text)

Max Activating Token Index: 421

Text #18

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.0744. Min Act: -0.1700

Data Index: 3950768 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 4.2040. Min Range: -4.2040

Max Act: 4.1064. Min Act: -0.1700

Data Index: 7922753 (Open Web Text)

Max Activating Token Index: 750