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

Dataset: Open Web Text

Neuron 15 in Layer 5

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: 4.3843. Min Range: -4.3843

Max Act: 4.3843. Min Act: -0.1700

Data Index: 2594313 (Open Web Text)

Max Activating Token Index: 264

Text #1

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.9779. Min Act: -0.1700

Data Index: 4672558 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.9679. Min Act: -0.1700

Data Index: 4139381 (Open Web Text)

Max Activating Token Index: 813

Text #3

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.9512. Min Act: -0.1700

Data Index: 2319956 (Open Web Text)

Max Activating Token Index: 848

Text #4

Max Range: 4.3843. Min Range: -4.3843

Max Act: 4.0116. Min Act: -0.1700

Data Index: 4695682 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8789. Min Act: -0.1700

Data Index: 2151608 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.9252. Min Act: -0.1700

Data Index: 8399986 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8755. Min Act: -0.1700

Data Index: 6133057 (Open Web Text)

Max Activating Token Index: 980

Text #8

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8682. Min Act: -0.1700

Data Index: 712367 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8596. Min Act: -0.1700

Data Index: 3545891 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8901. Min Act: -0.1700

Data Index: 5808846 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8609. Min Act: -0.1700

Data Index: 3234400 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8731. Min Act: -0.1700

Data Index: 7662962 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8535. Min Act: -0.1700

Data Index: 3451777 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8347. Min Act: -0.1700

Data Index: 197270 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8568. Min Act: -0.1700

Data Index: 4039682 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8004. Min Act: -0.1700

Data Index: 5195946 (Open Web Text)

Max Activating Token Index: 609

Text #17

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.7917. Min Act: -0.1700

Data Index: 1184680 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8197. Min Act: -0.1700

Data Index: 110364 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 4.3843. Min Range: -4.3843

Max Act: 3.8199. Min Act: -0.1700

Data Index: 90072 (Open Web Text)

Max Activating Token Index: 466