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

Dataset: Open Web Text

Neuron 2812 in Layer 4

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: 4.0731. Min Range: -4.0731

Max Act: 4.0544. Min Act: -0.1700

Data Index: 6616863 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 4.0731. Min Range: -4.0731

Max Act: 4.0731. Min Act: -0.1700

Data Index: 2010002 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.9826. Min Act: -0.1700

Data Index: 3580527 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.9797. Min Act: -0.1700

Data Index: 57833 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8982. Min Act: -0.1700

Data Index: 156329 (Open Web Text)

Max Activating Token Index: 304

Text #5

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.9403. Min Act: -0.1700

Data Index: 1721849 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.9767. Min Act: -0.1700

Data Index: 1906162 (Open Web Text)

Max Activating Token Index: 536

Text #7

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.9137. Min Act: -0.1700

Data Index: 8792456 (Open Web Text)

Max Activating Token Index: 588

Text #8

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8576. Min Act: -0.1700

Data Index: 3495925 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.7731. Min Act: -0.1700

Data Index: 8147085 (Open Web Text)

Max Activating Token Index: 728

Text #10

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8363. Min Act: -0.1700

Data Index: 7140846 (Open Web Text)

Max Activating Token Index: 816

Text #11

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8446. Min Act: -0.1700

Data Index: 897222 (Open Web Text)

Max Activating Token Index: 337

Text #12

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8548. Min Act: -0.1700

Data Index: 3397609 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.7119. Min Act: -0.1700

Data Index: 4054941 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.7827. Min Act: -0.1700

Data Index: 618605 (Open Web Text)

Max Activating Token Index: 388

Text #15

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8254. Min Act: -0.1700

Data Index: 88581 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8004. Min Act: -0.1700

Data Index: 6266512 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.8323. Min Act: -0.1700

Data Index: 1995075 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.7764. Min Act: -0.1700

Data Index: 3048331 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 4.0731. Min Range: -4.0731

Max Act: 3.7534. Min Act: -0.1700

Data Index: 7474805 (Open Web Text)

Max Activating Token Index: 353