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

Dataset: Open Web Text

Neuron 2620 in Layer 6

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: 4.2433. Min Range: -4.2433

Max Act: 4.1999. Min Act: -0.1700

Data Index: 7159512 (Open Web Text)

Max Activating Token Index: 733

Text #1

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.2299. Min Act: -0.1700

Data Index: 1636635 (Open Web Text)

Max Activating Token Index: 794

Text #2

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.2433. Min Act: -0.1700

Data Index: 145782 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.1892. Min Act: -0.1700

Data Index: 6691362 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.2034. Min Act: -0.1700

Data Index: 2003485 (Open Web Text)

Max Activating Token Index: 855

Text #5

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.1556. Min Act: -0.1700

Data Index: 1085465 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.1747. Min Act: -0.1700

Data Index: 7205473 (Open Web Text)

Max Activating Token Index: 533

Text #7

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.1220. Min Act: -0.1700

Data Index: 418297 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.1236. Min Act: -0.1700

Data Index: 5100711 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.0923. Min Act: -0.1700

Data Index: 5100712 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.0246. Min Act: -0.1700

Data Index: 7290523 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.0571. Min Act: -0.1700

Data Index: 7054305 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.0243. Min Act: -0.1700

Data Index: 3471342 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.0454. Min Act: -0.1700

Data Index: 53037 (Open Web Text)

Max Activating Token Index: 139

Text #14

Max Range: 4.2433. Min Range: -4.2433

Max Act: 4.0542. Min Act: -0.1700

Data Index: 2417185 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 4.2433. Min Range: -4.2433

Max Act: 3.9769. Min Act: -0.1700

Data Index: 5973912 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 4.2433. Min Range: -4.2433

Max Act: 3.9279. Min Act: -0.1700

Data Index: 270767 (Open Web Text)

Max Activating Token Index: 312

Text #17

Max Range: 4.2433. Min Range: -4.2433

Max Act: 3.9433. Min Act: -0.1700

Data Index: 6976929 (Open Web Text)

Max Activating Token Index: 857

Text #18

Max Range: 4.2433. Min Range: -4.2433

Max Act: 3.9371. Min Act: -0.1700

Data Index: 198006 (Open Web Text)

Max Activating Token Index: 580

Text #19

Max Range: 4.2433. Min Range: -4.2433

Max Act: 3.9487. Min Act: -0.1700

Data Index: 3006690 (Open Web Text)

Max Activating Token Index: 27