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

Dataset: Open Web Text

Neuron 733 in Layer 3

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: 4.8640. Min Range: -4.8640

Max Act: 4.8640. Min Act: -0.1700

Data Index: 1729386 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.7535. Min Act: -0.1700

Data Index: 986257 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6526. Min Act: -0.1700

Data Index: 5910870 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6812. Min Act: -0.1700

Data Index: 3613282 (Open Web Text)

Max Activating Token Index: 108

Text #4

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6876. Min Act: -0.1700

Data Index: 4366911 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6428. Min Act: -0.1700

Data Index: 6444291 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6088. Min Act: -0.1700

Data Index: 6628075 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6873. Min Act: -0.1700

Data Index: 2873258 (Open Web Text)

Max Activating Token Index: 812

Text #8

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6132. Min Act: -0.1700

Data Index: 6823777 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6117. Min Act: -0.1700

Data Index: 7592868 (Open Web Text)

Max Activating Token Index: 749

Text #10

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6130. Min Act: -0.1700

Data Index: 6742693 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6166. Min Act: -0.1700

Data Index: 5849719 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5620. Min Act: -0.1700

Data Index: 5655612 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5865. Min Act: -0.1700

Data Index: 656583 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5576. Min Act: -0.1700

Data Index: 8576758 (Open Web Text)

Max Activating Token Index: 945

Text #15

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.6100. Min Act: -0.1700

Data Index: 2842493 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5753. Min Act: -0.1700

Data Index: 4241776 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5646. Min Act: -0.1700

Data Index: 5353676 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5331. Min Act: -0.1700

Data Index: 3053909 (Open Web Text)

Max Activating Token Index: 150

Text #19

Max Range: 4.8640. Min Range: -4.8640

Max Act: 4.5284. Min Act: -0.1700

Data Index: 5288690 (Open Web Text)

Max Activating Token Index: 208