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

Dataset: Open Web Text

Neuron 3052 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: 3.2389. Min Range: -3.2389

Max Act: 3.2389. Min Act: -0.1700

Data Index: 6071784 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.2112. Min Act: -0.1700

Data Index: 3834488 (Open Web Text)

Max Activating Token Index: 45

Text #2

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.1330. Min Act: -0.1700

Data Index: 5829004 (Open Web Text)

Max Activating Token Index: 959

Text #3

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.1315. Min Act: -0.1700

Data Index: 4213810 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.1034. Min Act: -0.1700

Data Index: 7518323 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.1257. Min Act: -0.1700

Data Index: 7210195 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0558. Min Act: -0.1700

Data Index: 4420087 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0769. Min Act: -0.1700

Data Index: 6237037 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0491. Min Act: -0.1700

Data Index: 6240152 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0235. Min Act: -0.1700

Data Index: 420981 (Open Web Text)

Max Activating Token Index: 817

Text #10

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0432. Min Act: -0.1700

Data Index: 5513477 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0263. Min Act: -0.1700

Data Index: 5671449 (Open Web Text)

Max Activating Token Index: 311

Text #12

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0132. Min Act: -0.1700

Data Index: 1409167 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0097. Min Act: -0.1700

Data Index: 3509374 (Open Web Text)

Max Activating Token Index: 95

Text #14

Max Range: 3.2389. Min Range: -3.2389

Max Act: 3.0073. Min Act: -0.1700

Data Index: 3962512 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 3.2389. Min Range: -3.2389

Max Act: 2.9850. Min Act: -0.1700

Data Index: 5471219 (Open Web Text)

Max Activating Token Index: 739

Text #16

Max Range: 3.2389. Min Range: -3.2389

Max Act: 2.9643. Min Act: -0.1700

Data Index: 6122034 (Open Web Text)

Max Activating Token Index: 28

Text #17

Max Range: 3.2389. Min Range: -3.2389

Max Act: 2.9358. Min Act: -0.1700

Data Index: 541751 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 3.2389. Min Range: -3.2389

Max Act: 2.9348. Min Act: -0.1700

Data Index: 1311393 (Open Web Text)

Max Activating Token Index: 573

Text #19

Max Range: 3.2389. Min Range: -3.2389

Max Act: 2.9242. Min Act: -0.1700

Data Index: 3968434 (Open Web Text)

Max Activating Token Index: 1022