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

Dataset: Open Web Text

Neuron 444 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: 3.9769. Min Range: -3.9769

Max Act: 3.9503. Min Act: -0.1700

Data Index: 8774252 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.9769. Min Act: -0.1700

Data Index: 4047963 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.9062. Min Act: -0.1700

Data Index: 7985196 (Open Web Text)

Max Activating Token Index: 635

Text #3

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8686. Min Act: -0.1700

Data Index: 7216452 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8637. Min Act: -0.1700

Data Index: 901653 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8804. Min Act: -0.1700

Data Index: 546513 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8779. Min Act: -0.1700

Data Index: 8774260 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8581. Min Act: -0.1700

Data Index: 1837219 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8515. Min Act: -0.1700

Data Index: 7186855 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8484. Min Act: -0.1700

Data Index: 5277060 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8183. Min Act: -0.1700

Data Index: 8774262 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8356. Min Act: -0.1700

Data Index: 8307921 (Open Web Text)

Max Activating Token Index: 670

Text #12

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8181. Min Act: -0.1700

Data Index: 260746 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8445. Min Act: -0.1700

Data Index: 7325353 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8479. Min Act: -0.1700

Data Index: 3739297 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8223. Min Act: -0.1700

Data Index: 906645 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8247. Min Act: -0.1700

Data Index: 3513119 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8307. Min Act: -0.1700

Data Index: 2897765 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8382. Min Act: -0.1700

Data Index: 2735010 (Open Web Text)

Max Activating Token Index: 865

Text #19

Max Range: 3.9769. Min Range: -3.9769

Max Act: 3.8110. Min Act: -0.1700

Data Index: 7160771 (Open Web Text)

Max Activating Token Index: 453