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

Dataset: Open Web Text

Neuron 1471 in Layer 1

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: 3.7863. Min Range: -3.7863

Max Act: 3.7863. Min Act: -0.1700

Data Index: 2621737 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7782. Min Act: -0.1700

Data Index: 4230979 (Open Web Text)

Max Activating Token Index: 278

Text #2

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7859. Min Act: -0.1700

Data Index: 3043124 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7345. Min Act: -0.1700

Data Index: 6909906 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7442. Min Act: -0.1700

Data Index: 8237241 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7556. Min Act: -0.1700

Data Index: 8010049 (Open Web Text)

Max Activating Token Index: 171

Text #6

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7604. Min Act: -0.1700

Data Index: 7600431 (Open Web Text)

Max Activating Token Index: 42

Text #7

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7634. Min Act: -0.1700

Data Index: 5001999 (Open Web Text)

Max Activating Token Index: 369

Text #8

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7588. Min Act: -0.1700

Data Index: 7440348 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7398. Min Act: -0.1700

Data Index: 4388908 (Open Web Text)

Max Activating Token Index: 802

Text #10

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7542. Min Act: -0.1700

Data Index: 3268992 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7365. Min Act: -0.1700

Data Index: 2386446 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7704. Min Act: -0.1700

Data Index: 1249073 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7494. Min Act: -0.1700

Data Index: 2110271 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7668. Min Act: -0.1700

Data Index: 2595122 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7364. Min Act: -0.1700

Data Index: 4191525 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7603. Min Act: -0.1700

Data Index: 6471158 (Open Web Text)

Max Activating Token Index: 438

Text #17

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7613. Min Act: -0.1700

Data Index: 5720184 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7416. Min Act: -0.1700

Data Index: 2438862 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.7863. Min Range: -3.7863

Max Act: 3.7596. Min Act: -0.1700

Data Index: 1918980 (Open Web Text)

Max Activating Token Index: 301