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

Dataset: Open Web Text

Neuron 2775 in Layer 1

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: 3.3459. Min Range: -3.3459

Max Act: 3.3400. Min Act: -0.1700

Data Index: 4604209 (Open Web Text)

Max Activating Token Index: 541

Text #1

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.3459. Min Act: -0.1700

Data Index: 4295330 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.3142. Min Act: -0.1700

Data Index: 3495967 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.3122. Min Act: -0.1700

Data Index: 568792 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2773. Min Act: -0.1700

Data Index: 5024922 (Open Web Text)

Max Activating Token Index: 304

Text #5

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2882. Min Act: -0.1700

Data Index: 2597798 (Open Web Text)

Max Activating Token Index: 216

Text #6

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2784. Min Act: -0.1700

Data Index: 3308570 (Open Web Text)

Max Activating Token Index: 463

Text #7

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1218644 (Open Web Text)

Max Activating Token Index: 379

Text #8

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2211. Min Act: -0.1700

Data Index: 3115680 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.2011. Min Act: -0.1700

Data Index: 348965 (Open Web Text)

Max Activating Token Index: 347

Text #10

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1813. Min Act: -0.1700

Data Index: 6277729 (Open Web Text)

Max Activating Token Index: 669

Text #11

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1984. Min Act: -0.1700

Data Index: 3246409 (Open Web Text)

Max Activating Token Index: 379

Text #12

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1887. Min Act: -0.1700

Data Index: 8762741 (Open Web Text)

Max Activating Token Index: 400

Text #13

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1775. Min Act: -0.1700

Data Index: 2917857 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1568. Min Act: -0.1700

Data Index: 763483 (Open Web Text)

Max Activating Token Index: 308

Text #15

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1701. Min Act: -0.1700

Data Index: 1685061 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1709. Min Act: -0.1700

Data Index: 2058822 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1747. Min Act: -0.1700

Data Index: 7354818 (Open Web Text)

Max Activating Token Index: 218

Text #18

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1439. Min Act: -0.1700

Data Index: 5930613 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 3.3459. Min Range: -3.3459

Max Act: 3.1496. Min Act: -0.1700

Data Index: 205486 (Open Web Text)

Max Activating Token Index: 470