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

Dataset: Open Web Text

Neuron 346 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: 4.0571. Min Range: -4.0571

Max Act: 4.0571. Min Act: -0.1700

Data Index: 135014 (Open Web Text)

Max Activating Token Index: 844

Text #1

Max Range: 4.0571. Min Range: -4.0571

Max Act: 4.0489. Min Act: -0.1700

Data Index: 5144809 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9942. Min Act: -0.1700

Data Index: 2984776 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 4.0571. Min Range: -4.0571

Max Act: 4.0031. Min Act: -0.1700

Data Index: 7448499 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 4.0571. Min Range: -4.0571

Max Act: 4.0326. Min Act: -0.1700

Data Index: 1390993 (Open Web Text)

Max Activating Token Index: 908

Text #5

Max Range: 4.0571. Min Range: -4.0571

Max Act: 4.0007. Min Act: -0.1700

Data Index: 2243376 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 4.0571. Min Range: -4.0571

Max Act: 4.0008. Min Act: -0.1700

Data Index: 5594275 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9906. Min Act: -0.1700

Data Index: 8250373 (Open Web Text)

Max Activating Token Index: 470

Text #8

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9753. Min Act: -0.1700

Data Index: 8315144 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9654. Min Act: -0.1700

Data Index: 4069022 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9876. Min Act: -0.1700

Data Index: 4633709 (Open Web Text)

Max Activating Token Index: 586

Text #11

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9613. Min Act: -0.1700

Data Index: 1760549 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9236. Min Act: -0.1700

Data Index: 6022812 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9898. Min Act: -0.1700

Data Index: 2646514 (Open Web Text)

Max Activating Token Index: 600

Text #14

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9336. Min Act: -0.1700

Data Index: 917641 (Open Web Text)

Max Activating Token Index: 1011

Text #15

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9536. Min Act: -0.1700

Data Index: 2742004 (Open Web Text)

Max Activating Token Index: 510

Text #16

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9380. Min Act: -0.1700

Data Index: 5305519 (Open Web Text)

Max Activating Token Index: 665

Text #17

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9436. Min Act: -0.1700

Data Index: 1517680 (Open Web Text)

Max Activating Token Index: 696

Text #18

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9582. Min Act: -0.1700

Data Index: 497348 (Open Web Text)

Max Activating Token Index: 873

Text #19

Max Range: 4.0571. Min Range: -4.0571

Max Act: 3.9276. Min Act: -0.1700

Data Index: 4243533 (Open Web Text)

Max Activating Token Index: 883