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

Dataset: Open Web Text

Neuron 677 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: 1.4604. Min Range: -1.4604

Max Act: 1.4604. Min Act: -0.1700

Data Index: 6737884 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.4405. Min Act: -0.1700

Data Index: 5304954 (Open Web Text)

Max Activating Token Index: 965

Text #2

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.4225. Min Act: -0.1700

Data Index: 4652208 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.4268. Min Act: -0.1700

Data Index: 3653677 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3956. Min Act: -0.1700

Data Index: 4899327 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3621. Min Act: -0.1700

Data Index: 8202023 (Open Web Text)

Max Activating Token Index: 176

Text #6

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3336. Min Act: -0.1700

Data Index: 1630818 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3456. Min Act: -0.1700

Data Index: 2122045 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3269. Min Act: -0.1700

Data Index: 8811709 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.3024. Min Act: -0.1700

Data Index: 5128766 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2709. Min Act: -0.1700

Data Index: 6042735 (Open Web Text)

Max Activating Token Index: 565

Text #11

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2906. Min Act: -0.1700

Data Index: 8439291 (Open Web Text)

Max Activating Token Index: 549

Text #12

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2779. Min Act: -0.1700

Data Index: 1277819 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2707. Min Act: -0.1700

Data Index: 494977 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2622. Min Act: -0.1700

Data Index: 4288492 (Open Web Text)

Max Activating Token Index: 972

Text #15

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2718. Min Act: -0.1700

Data Index: 2565961 (Open Web Text)

Max Activating Token Index: 585

Text #16

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2562. Min Act: -0.1700

Data Index: 4150389 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2718. Min Act: -0.1700

Data Index: 2683756 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2690. Min Act: -0.1700

Data Index: 5574810 (Open Web Text)

Max Activating Token Index: 321

Text #19

Max Range: 1.4604. Min Range: -1.4604

Max Act: 1.2600. Min Act: -0.1700

Data Index: 890267 (Open Web Text)

Max Activating Token Index: 625