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

Dataset: Open Web Text

Neuron 760 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: 4.8517. Min Range: -4.8517

Max Act: 4.8517. Min Act: -0.1700

Data Index: 6873716 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.8291. Min Act: -0.1700

Data Index: 6559403 (Open Web Text)

Max Activating Token Index: 1001

Text #2

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7940. Min Act: -0.1700

Data Index: 1923093 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7767. Min Act: -0.1700

Data Index: 3888493 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7603. Min Act: -0.1700

Data Index: 8686996 (Open Web Text)

Max Activating Token Index: 365

Text #5

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7576. Min Act: -0.1700

Data Index: 6544971 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7410. Min Act: -0.1700

Data Index: 5878998 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7423. Min Act: -0.1700

Data Index: 5158242 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7612. Min Act: -0.1700

Data Index: 5087053 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7414. Min Act: -0.1700

Data Index: 8828401 (Open Web Text)

Max Activating Token Index: 844

Text #10

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7548. Min Act: -0.1700

Data Index: 8147528 (Open Web Text)

Max Activating Token Index: 480

Text #11

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7298. Min Act: -0.1700

Data Index: 5874464 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7114. Min Act: -0.1700

Data Index: 765154 (Open Web Text)

Max Activating Token Index: 390

Text #13

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7296. Min Act: -0.1700

Data Index: 619149 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7246. Min Act: -0.1700

Data Index: 2288255 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7102. Min Act: -0.1700

Data Index: 2210014 (Open Web Text)

Max Activating Token Index: 392

Text #16

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7186. Min Act: -0.1700

Data Index: 5904652 (Open Web Text)

Max Activating Token Index: 489

Text #17

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7052. Min Act: -0.1700

Data Index: 6044901 (Open Web Text)

Max Activating Token Index: 770

Text #18

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7125. Min Act: -0.1700

Data Index: 2002581 (Open Web Text)

Max Activating Token Index: 941

Text #19

Max Range: 4.8517. Min Range: -4.8517

Max Act: 4.7185. Min Act: -0.1700

Data Index: 7521402 (Open Web Text)

Max Activating Token Index: 873