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

Dataset: Open Web Text

Neuron 577 in Layer 4

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: 3.5868. Min Range: -3.5868

Max Act: 3.5868. Min Act: -0.1700

Data Index: 4074418 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.5328. Min Act: -0.1700

Data Index: 7437142 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.5198. Min Act: -0.1700

Data Index: 6185495 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.4195. Min Act: -0.1700

Data Index: 19638 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.3300. Min Act: -0.1700

Data Index: 6752610 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.3220. Min Act: -0.1700

Data Index: 4738422 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2910. Min Act: -0.1700

Data Index: 466944 (Open Web Text)

Max Activating Token Index: 536

Text #7

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2842. Min Act: -0.1700

Data Index: 3944589 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2611. Min Act: -0.1700

Data Index: 7161879 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2847. Min Act: -0.1700

Data Index: 5158155 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2828. Min Act: -0.1700

Data Index: 7687009 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2590. Min Act: -0.1700

Data Index: 1357589 (Open Web Text)

Max Activating Token Index: 280

Text #12

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2707. Min Act: -0.1700

Data Index: 1853334 (Open Web Text)

Max Activating Token Index: 694

Text #13

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2649. Min Act: -0.1700

Data Index: 2652333 (Open Web Text)

Max Activating Token Index: 917

Text #14

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2667. Min Act: -0.1700

Data Index: 6204809 (Open Web Text)

Max Activating Token Index: 998

Text #15

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2423. Min Act: -0.1700

Data Index: 7381431 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2718. Min Act: -0.1700

Data Index: 4667277 (Open Web Text)

Max Activating Token Index: 733

Text #17

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2598. Min Act: -0.1700

Data Index: 2451392 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2451. Min Act: -0.1700

Data Index: 319516 (Open Web Text)

Max Activating Token Index: 967

Text #19

Max Range: 3.5868. Min Range: -3.5868

Max Act: 3.2587. Min Act: -0.1700

Data Index: 1532534 (Open Web Text)

Max Activating Token Index: 428