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

Dataset: Open Web Text

Neuron 641 in Layer 2

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: 4.8722. Min Range: -4.8722

Max Act: 4.8722. Min Act: -0.1700

Data Index: 3489426 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.7770. Min Act: -0.1700

Data Index: 3664091 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.7454. Min Act: -0.1700

Data Index: 7245561 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.7371. Min Act: -0.1700

Data Index: 3105912 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.7439. Min Act: -0.1700

Data Index: 4861967 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.6750. Min Act: -0.1700

Data Index: 7644206 (Open Web Text)

Max Activating Token Index: 283

Text #6

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.6141. Min Act: -0.1700

Data Index: 929337 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5558. Min Act: -0.1700

Data Index: 7645959 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5445. Min Act: -0.1700

Data Index: 6900584 (Open Web Text)

Max Activating Token Index: 955

Text #9

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.4367. Min Act: -0.1700

Data Index: 1429880 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.4574. Min Act: -0.1700

Data Index: 8689791 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5637. Min Act: -0.1700

Data Index: 3232665 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5019. Min Act: -0.1700

Data Index: 5268485 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.4647. Min Act: -0.1700

Data Index: 3868883 (Open Web Text)

Max Activating Token Index: 918

Text #14

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.4338. Min Act: -0.1700

Data Index: 2457538 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5575. Min Act: -0.1700

Data Index: 7430444 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5074. Min Act: -0.1700

Data Index: 6071688 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.4684. Min Act: -0.1700

Data Index: 1689403 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.5120. Min Act: -0.1700

Data Index: 3977956 (Open Web Text)

Max Activating Token Index: 328

Text #19

Max Range: 4.8722. Min Range: -4.8722

Max Act: 4.4340. Min Act: -0.1700

Data Index: 8287671 (Open Web Text)

Max Activating Token Index: 158