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

Dataset: Open Web Text

Neuron 109 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: 4.1940. Min Range: -4.1940

Max Act: 4.1940. Min Act: -0.1700

Data Index: 7817848 (Open Web Text)

Max Activating Token Index: 660

Text #1

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.9172. Min Act: -0.1700

Data Index: 4885872 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.9039. Min Act: -0.1700

Data Index: 5702906 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.9262. Min Act: -0.1700

Data Index: 3745690 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.9183. Min Act: -0.1700

Data Index: 5131252 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8825. Min Act: -0.1700

Data Index: 7871113 (Open Web Text)

Max Activating Token Index: 470

Text #6

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8888. Min Act: -0.1700

Data Index: 723716 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8796. Min Act: -0.1700

Data Index: 8728016 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8997. Min Act: -0.1700

Data Index: 8327082 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8659. Min Act: -0.1700

Data Index: 2098729 (Open Web Text)

Max Activating Token Index: 869

Text #10

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8278. Min Act: -0.1700

Data Index: 1578452 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8283. Min Act: -0.1700

Data Index: 6070798 (Open Web Text)

Max Activating Token Index: 783

Text #12

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8237. Min Act: -0.1700

Data Index: 2021941 (Open Web Text)

Max Activating Token Index: 957

Text #13

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.7982. Min Act: -0.1700

Data Index: 3382709 (Open Web Text)

Max Activating Token Index: 978

Text #14

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.7748. Min Act: -0.1700

Data Index: 7223619 (Open Web Text)

Max Activating Token Index: 436

Text #15

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.7781. Min Act: -0.1700

Data Index: 308538 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.7889. Min Act: -0.1700

Data Index: 2866195 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.7826. Min Act: -0.1700

Data Index: 2213883 (Open Web Text)

Max Activating Token Index: 726

Text #18

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.7989. Min Act: -0.1700

Data Index: 6973269 (Open Web Text)

Max Activating Token Index: 666

Text #19

Max Range: 4.1940. Min Range: -4.1940

Max Act: 3.8019. Min Act: -0.1700

Data Index: 438723 (Open Web Text)

Max Activating Token Index: 709