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

Dataset: Open Web Text

Neuron 1580 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: 4.8491. Min Range: -4.8491

Max Act: 4.8491. Min Act: -0.1700

Data Index: 2997850 (Open Web Text)

Max Activating Token Index: 506

Text #1

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.8213. Min Act: -0.1700

Data Index: 4523801 (Open Web Text)

Max Activating Token Index: 96

Text #2

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.8236. Min Act: -0.1700

Data Index: 6064372 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7844. Min Act: -0.1700

Data Index: 8587647 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7637. Min Act: -0.1700

Data Index: 5888443 (Open Web Text)

Max Activating Token Index: 844

Text #5

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7590. Min Act: -0.1700

Data Index: 8189075 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7669. Min Act: -0.1700

Data Index: 7804157 (Open Web Text)

Max Activating Token Index: 704

Text #7

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7342. Min Act: -0.1700

Data Index: 1383906 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7339. Min Act: -0.1700

Data Index: 7273234 (Open Web Text)

Max Activating Token Index: 90

Text #9

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7498. Min Act: -0.1700

Data Index: 7830900 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7191. Min Act: -0.1700

Data Index: 8242436 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7063. Min Act: -0.1700

Data Index: 8476024 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7144. Min Act: -0.1700

Data Index: 8537648 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7197. Min Act: -0.1700

Data Index: 8634001 (Open Web Text)

Max Activating Token Index: 770

Text #14

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7047. Min Act: -0.1700

Data Index: 5397060 (Open Web Text)

Max Activating Token Index: 358

Text #15

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7159. Min Act: -0.1700

Data Index: 4788755 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7147. Min Act: -0.1700

Data Index: 6172637 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.7000. Min Act: -0.1700

Data Index: 2519435 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.6998. Min Act: -0.1700

Data Index: 2902100 (Open Web Text)

Max Activating Token Index: 170

Text #19

Max Range: 4.8491. Min Range: -4.8491

Max Act: 4.6829. Min Act: -0.1700

Data Index: 3162335 (Open Web Text)

Max Activating Token Index: 138