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

Dataset: Open Web Text

Neuron 1569 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: 4.8641. Min Range: -4.8641

Max Act: 4.8641. Min Act: -0.1700

Data Index: 4637508 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7600. Min Act: -0.1700

Data Index: 4965300 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.7118. Min Act: -0.1700

Data Index: 2100869 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6883. Min Act: -0.1700

Data Index: 2180473 (Open Web Text)

Max Activating Token Index: 789

Text #4

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6228. Min Act: -0.1700

Data Index: 964761 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5929. Min Act: -0.1700

Data Index: 5332745 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6290. Min Act: -0.1700

Data Index: 2028625 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6032. Min Act: -0.1700

Data Index: 6333278 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5767. Min Act: -0.1700

Data Index: 2112760 (Open Web Text)

Max Activating Token Index: 849

Text #9

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5541. Min Act: -0.1700

Data Index: 3898328 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5610. Min Act: -0.1700

Data Index: 1616616 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.6035. Min Act: -0.1700

Data Index: 913972 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5884. Min Act: -0.1700

Data Index: 4112042 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5800. Min Act: -0.1700

Data Index: 3481399 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5617. Min Act: -0.1700

Data Index: 4061057 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5360. Min Act: -0.1700

Data Index: 3568725 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5099. Min Act: -0.1700

Data Index: 7679985 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5490. Min Act: -0.1700

Data Index: 3171324 (Open Web Text)

Max Activating Token Index: 97

Text #18

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5368. Min Act: -0.1700

Data Index: 5814641 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 4.8641. Min Range: -4.8641

Max Act: 4.5104. Min Act: -0.1700

Data Index: 3145062 (Open Web Text)

Max Activating Token Index: 250