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

Dataset: Open Web Text

Neuron 2416 in Layer 6

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: 4.6660. Min Range: -4.6660

Max Act: 4.6660. Min Act: -0.1700

Data Index: 6462305 (Open Web Text)

Max Activating Token Index: 738

Text #1

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.5723. Min Act: -0.1700

Data Index: 7529394 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.5403. Min Act: -0.1700

Data Index: 598573 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.4789. Min Act: -0.1700

Data Index: 4892183 (Open Web Text)

Max Activating Token Index: 904

Text #4

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.4766. Min Act: -0.1700

Data Index: 2378400 (Open Web Text)

Max Activating Token Index: 427

Text #5

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.4618. Min Act: -0.1700

Data Index: 6070996 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.4441. Min Act: -0.1700

Data Index: 7945283 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.4368. Min Act: -0.1700

Data Index: 4894766 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3947. Min Act: -0.1700

Data Index: 1601582 (Open Web Text)

Max Activating Token Index: 298

Text #9

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.4457. Min Act: -0.1700

Data Index: 8173916 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3486. Min Act: -0.1700

Data Index: 1900825 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3498. Min Act: -0.1700

Data Index: 1854759 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3877. Min Act: -0.1700

Data Index: 5591700 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3565. Min Act: -0.1700

Data Index: 247837 (Open Web Text)

Max Activating Token Index: 917

Text #14

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.2993. Min Act: -0.1700

Data Index: 8170544 (Open Web Text)

Max Activating Token Index: 600

Text #15

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3341. Min Act: -0.1700

Data Index: 6068783 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3137. Min Act: -0.1700

Data Index: 3098332 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.2515. Min Act: -0.1700

Data Index: 767015 (Open Web Text)

Max Activating Token Index: 326

Text #18

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.2656. Min Act: -0.1700

Data Index: 3491294 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 4.6660. Min Range: -4.6660

Max Act: 4.3158. Min Act: -0.1700

Data Index: 3640067 (Open Web Text)

Max Activating Token Index: 274