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

Dataset: Open Web Text

Neuron 1316 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: 4.5486. Min Range: -4.5486

Max Act: 4.5486. Min Act: -0.1700

Data Index: 5901033 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4566. Min Act: -0.1700

Data Index: 7960161 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4484. Min Act: -0.1700

Data Index: 1832724 (Open Web Text)

Max Activating Token Index: 504

Text #3

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4625. Min Act: -0.1700

Data Index: 6176807 (Open Web Text)

Max Activating Token Index: 711

Text #4

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4353. Min Act: -0.1700

Data Index: 6209979 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4163. Min Act: -0.1700

Data Index: 7440146 (Open Web Text)

Max Activating Token Index: 832

Text #6

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4309. Min Act: -0.1700

Data Index: 4739336 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4119. Min Act: -0.1700

Data Index: 724401 (Open Web Text)

Max Activating Token Index: 839

Text #8

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4802. Min Act: -0.1700

Data Index: 5957764 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4102. Min Act: -0.1700

Data Index: 5316737 (Open Web Text)

Max Activating Token Index: 425

Text #10

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4055. Min Act: -0.1700

Data Index: 4409417 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3693. Min Act: -0.1700

Data Index: 4743194 (Open Web Text)

Max Activating Token Index: 858

Text #12

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3773. Min Act: -0.1700

Data Index: 5927093 (Open Web Text)

Max Activating Token Index: 655

Text #13

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3913. Min Act: -0.1700

Data Index: 5480519 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3831. Min Act: -0.1700

Data Index: 618154 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4006. Min Act: -0.1700

Data Index: 3120709 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3813. Min Act: -0.1700

Data Index: 7030023 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3714. Min Act: -0.1700

Data Index: 7361241 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.3749. Min Act: -0.1700

Data Index: 4822592 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 4.5486. Min Range: -4.5486

Max Act: 4.4412. Min Act: -0.1700

Data Index: 4038713 (Open Web Text)

Max Activating Token Index: 886