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

Dataset: Open Web Text

Neuron 2344 in Layer 2

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: 2.0568. Min Range: -2.0568

Max Act: 2.0568. Min Act: -0.1700

Data Index: 7020563 (Open Web Text)

Max Activating Token Index: 737

Text #1

Max Range: 2.0568. Min Range: -2.0568

Max Act: 2.0309. Min Act: -0.1699

Data Index: 2412693 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 2.0568. Min Range: -2.0568

Max Act: 2.0206. Min Act: -0.1700

Data Index: 2160236 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9928. Min Act: -0.1700

Data Index: 4947718 (Open Web Text)

Max Activating Token Index: 695

Text #4

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9905. Min Act: -0.1695

Data Index: 8346255 (Open Web Text)

Max Activating Token Index: 618

Text #5

Max Range: 2.0568. Min Range: -2.0568

Max Act: 2.0028. Min Act: -0.1700

Data Index: 5260396 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9780. Min Act: -0.1699

Data Index: 6998089 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9690. Min Act: -0.1700

Data Index: 1405486 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9837. Min Act: -0.1700

Data Index: 2034362 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9885. Min Act: -0.1700

Data Index: 2419291 (Open Web Text)

Max Activating Token Index: 960

Text #10

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9532. Min Act: -0.1700

Data Index: 8451724 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9651. Min Act: -0.1700

Data Index: 8585600 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9742. Min Act: -0.1700

Data Index: 6778293 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9802. Min Act: -0.1700

Data Index: 4970963 (Open Web Text)

Max Activating Token Index: 690

Text #14

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9588. Min Act: -0.1700

Data Index: 300041 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9686. Min Act: -0.1690

Data Index: 118478 (Open Web Text)

Max Activating Token Index: 136

Text #16

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9489. Min Act: -0.1700

Data Index: 6261514 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9484. Min Act: -0.1699

Data Index: 3428091 (Open Web Text)

Max Activating Token Index: 542

Text #18

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9335. Min Act: -0.1700

Data Index: 2310790 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9413. Min Act: -0.1662

Data Index: 3252187 (Open Web Text)

Max Activating Token Index: 766