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

Dataset: Open Web Text

Neuron 653 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: 3.8429. Min Range: -3.8429

Max Act: 3.8429. Min Act: -0.1700

Data Index: 964041 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.7803. Min Act: -0.1700

Data Index: 1524685 (Open Web Text)

Max Activating Token Index: 339

Text #2

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.7176. Min Act: -0.1700

Data Index: 8500791 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6771. Min Act: -0.1700

Data Index: 7573783 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6694. Min Act: -0.1700

Data Index: 4071677 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6793. Min Act: -0.1700

Data Index: 8500786 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6328. Min Act: -0.1700

Data Index: 6509624 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6598. Min Act: -0.1700

Data Index: 7563024 (Open Web Text)

Max Activating Token Index: 592

Text #8

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6461. Min Act: -0.1700

Data Index: 720439 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6600. Min Act: -0.1700

Data Index: 1773430 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6385. Min Act: -0.1700

Data Index: 194691 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6196. Min Act: -0.1700

Data Index: 790814 (Open Web Text)

Max Activating Token Index: 592

Text #12

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6212. Min Act: -0.1700

Data Index: 857519 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6028. Min Act: -0.1700

Data Index: 2514949 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.5871. Min Act: -0.1700

Data Index: 4955686 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6003. Min Act: -0.1700

Data Index: 722762 (Open Web Text)

Max Activating Token Index: 310

Text #16

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6130. Min Act: -0.1700

Data Index: 7753324 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6190. Min Act: -0.1700

Data Index: 6046251 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.5721. Min Act: -0.1700

Data Index: 293301 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.5762. Min Act: -0.1700

Data Index: 5402090 (Open Web Text)

Max Activating Token Index: 364