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

Dataset: Open Web Text

Neuron 1715 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: 3.3634. Min Range: -3.3634

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1767727 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 3.3634. Min Range: -3.3634

Max Act: 3.1586. Min Act: -0.1700

Data Index: 6628364 (Open Web Text)

Max Activating Token Index: 797

Text #2

Max Range: 3.3634. Min Range: -3.3634

Max Act: 3.0002. Min Act: -0.1700

Data Index: 557449 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.9430. Min Act: -0.1700

Data Index: 8115789 (Open Web Text)

Max Activating Token Index: 912

Text #4

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8979. Min Act: -0.1700

Data Index: 5533306 (Open Web Text)

Max Activating Token Index: 816

Text #5

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8860. Min Act: -0.1700

Data Index: 8115793 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.9228. Min Act: -0.1700

Data Index: 8829000 (Open Web Text)

Max Activating Token Index: 840

Text #7

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8815. Min Act: -0.1700

Data Index: 5533302 (Open Web Text)

Max Activating Token Index: 896

Text #8

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8794. Min Act: -0.1700

Data Index: 5533310 (Open Web Text)

Max Activating Token Index: 747

Text #9

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.9114. Min Act: -0.1700

Data Index: 5533317 (Open Web Text)

Max Activating Token Index: 748

Text #10

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8634. Min Act: -0.1700

Data Index: 6611969 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8790. Min Act: -0.1700

Data Index: 8434676 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8811. Min Act: -0.1700

Data Index: 3255711 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8704. Min Act: -0.1700

Data Index: 5533307 (Open Web Text)

Max Activating Token Index: 688

Text #14

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8395. Min Act: -0.1700

Data Index: 5533298 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8544. Min Act: -0.1700

Data Index: 5533314 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8510. Min Act: -0.1700

Data Index: 5533304 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8278. Min Act: -0.1700

Data Index: 5533316 (Open Web Text)

Max Activating Token Index: 461

Text #18

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.8094. Min Act: -0.1700

Data Index: 5533301 (Open Web Text)

Max Activating Token Index: 924

Text #19

Max Range: 3.3634. Min Range: -3.3634

Max Act: 2.7456. Min Act: -0.1700

Data Index: 2523502 (Open Web Text)

Max Activating Token Index: 467