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

Dataset: Open Web Text

Neuron 369 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: 3.3723. Min Range: -3.3723

Max Act: 3.3723. Min Act: -0.1700

Data Index: 2756019 (Open Web Text)

Max Activating Token Index: 159

Text #1

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1002109 (Open Web Text)

Max Activating Token Index: 820

Text #2

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.3076. Min Act: -0.1700

Data Index: 881307 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2754. Min Act: -0.1700

Data Index: 8641071 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2642. Min Act: -0.1700

Data Index: 4417950 (Open Web Text)

Max Activating Token Index: 865

Text #5

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2452. Min Act: -0.1700

Data Index: 2465441 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2184. Min Act: -0.1700

Data Index: 5972598 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2208. Min Act: -0.1700

Data Index: 2488645 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1858. Min Act: -0.1700

Data Index: 5064740 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1819. Min Act: -0.1700

Data Index: 870190 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1879. Min Act: -0.1700

Data Index: 7016732 (Open Web Text)

Max Activating Token Index: 652

Text #11

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1717. Min Act: -0.1700

Data Index: 6836905 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1910. Min Act: -0.1700

Data Index: 4217886 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1587. Min Act: -0.1700

Data Index: 4636890 (Open Web Text)

Max Activating Token Index: 802

Text #14

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1665. Min Act: -0.1700

Data Index: 8701592 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1533. Min Act: -0.1700

Data Index: 8363724 (Open Web Text)

Max Activating Token Index: 212

Text #16

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1468. Min Act: -0.1700

Data Index: 249233 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1350. Min Act: -0.1700

Data Index: 8196454 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1466. Min Act: -0.1700

Data Index: 1332988 (Open Web Text)

Max Activating Token Index: 468

Text #19

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1699. Min Act: -0.1700

Data Index: 2899676 (Open Web Text)

Max Activating Token Index: 872