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

Dataset: Open Web Text

Neuron 2289 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: 3.9605. Min Range: -3.9605

Max Act: 3.9605. Min Act: -0.1700

Data Index: 4798259 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.9308. Min Act: -0.1700

Data Index: 2323436 (Open Web Text)

Max Activating Token Index: 729

Text #2

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.9282. Min Act: -0.1700

Data Index: 1960831 (Open Web Text)

Max Activating Token Index: 973

Text #3

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.9024. Min Act: -0.1700

Data Index: 2567577 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.9357. Min Act: -0.1700

Data Index: 1063091 (Open Web Text)

Max Activating Token Index: 391

Text #5

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.9159. Min Act: -0.1700

Data Index: 4051748 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.9148. Min Act: -0.1700

Data Index: 1801759 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.8186. Min Act: -0.1700

Data Index: 757150 (Open Web Text)

Max Activating Token Index: 1001

Text #8

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7708. Min Act: -0.1700

Data Index: 2690974 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7924. Min Act: -0.1700

Data Index: 5993493 (Open Web Text)

Max Activating Token Index: 156

Text #10

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7666. Min Act: -0.1700

Data Index: 4304764 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.8317. Min Act: -0.1700

Data Index: 2736968 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7370. Min Act: -0.1700

Data Index: 5443546 (Open Web Text)

Max Activating Token Index: 565

Text #13

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7622. Min Act: -0.1700

Data Index: 5296647 (Open Web Text)

Max Activating Token Index: 585

Text #14

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7889. Min Act: -0.1700

Data Index: 8706041 (Open Web Text)

Max Activating Token Index: 936

Text #15

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7612. Min Act: -0.1700

Data Index: 8783757 (Open Web Text)

Max Activating Token Index: 699

Text #16

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7606. Min Act: -0.1700

Data Index: 4144414 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7622. Min Act: -0.1700

Data Index: 4459448 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7630. Min Act: -0.1700

Data Index: 4701799 (Open Web Text)

Max Activating Token Index: 398

Text #19

Max Range: 3.9605. Min Range: -3.9605

Max Act: 3.7432. Min Act: -0.1700

Data Index: 642538 (Open Web Text)

Max Activating Token Index: 898