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

Dataset: Open Web Text

Neuron 1990 in Layer 3

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: 3.5433. Min Range: -3.5433

Max Act: 3.5433. Min Act: -0.1700

Data Index: 1069653 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.4249. Min Act: -0.1700

Data Index: 5687054 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.4138. Min Act: -0.1700

Data Index: 1722608 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.3323. Min Act: -0.1700

Data Index: 8483327 (Open Web Text)

Max Activating Token Index: 284

Text #4

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.3008. Min Act: -0.1700

Data Index: 2382894 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2836. Min Act: -0.1700

Data Index: 873353 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2999. Min Act: -0.1700

Data Index: 7765717 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2765. Min Act: -0.1700

Data Index: 7799714 (Open Web Text)

Max Activating Token Index: 978

Text #8

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1475628 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2006. Min Act: -0.1700

Data Index: 251545 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2016. Min Act: -0.1700

Data Index: 4112619 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2158. Min Act: -0.1700

Data Index: 6791516 (Open Web Text)

Max Activating Token Index: 147

Text #12

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2280. Min Act: -0.1700

Data Index: 3597449 (Open Web Text)

Max Activating Token Index: 691

Text #13

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2238. Min Act: -0.1700

Data Index: 3095712 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1217121 (Open Web Text)

Max Activating Token Index: 434

Text #15

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1876. Min Act: -0.1700

Data Index: 5123297 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1944. Min Act: -0.1700

Data Index: 1217122 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.2087. Min Act: -0.1700

Data Index: 5615871 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1789. Min Act: -0.1700

Data Index: 7620431 (Open Web Text)

Max Activating Token Index: 982

Text #19

Max Range: 3.5433. Min Range: -3.5433

Max Act: 3.1941. Min Act: -0.1700

Data Index: 4487381 (Open Web Text)

Max Activating Token Index: 479