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

Dataset: Open Web Text

Neuron 2882 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: 4.5556. Min Range: -4.5556

Max Act: 4.5556. Min Act: -0.1700

Data Index: 376475 (Open Web Text)

Max Activating Token Index: 931

Text #1

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.3825. Min Act: -0.1700

Data Index: 5197570 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.3089. Min Act: -0.1700

Data Index: 8341496 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.2508. Min Act: -0.1700

Data Index: 6065365 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.2713. Min Act: -0.1700

Data Index: 3781991 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.1519. Min Act: -0.1700

Data Index: 3001628 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.1338. Min Act: -0.1700

Data Index: 8809258 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.1299. Min Act: -0.1700

Data Index: 2098039 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0997. Min Act: -0.1700

Data Index: 3020177 (Open Web Text)

Max Activating Token Index: 991

Text #9

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0789. Min Act: -0.1700

Data Index: 6032934 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.1093. Min Act: -0.1700

Data Index: 4488602 (Open Web Text)

Max Activating Token Index: 186

Text #11

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0168. Min Act: -0.1700

Data Index: 7288213 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0140. Min Act: -0.1700

Data Index: 7966519 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 4.5556. Min Range: -4.5556

Max Act: 3.9930. Min Act: -0.1700

Data Index: 1824072 (Open Web Text)

Max Activating Token Index: 980

Text #14

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0241. Min Act: -0.1700

Data Index: 3902710 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0287. Min Act: -0.1700

Data Index: 2448527 (Open Web Text)

Max Activating Token Index: 265

Text #16

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0807. Min Act: -0.1700

Data Index: 6875665 (Open Web Text)

Max Activating Token Index: 196

Text #17

Max Range: 4.5556. Min Range: -4.5556

Max Act: 4.0033. Min Act: -0.1700

Data Index: 6166775 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 4.5556. Min Range: -4.5556

Max Act: 3.9731. Min Act: -0.1700

Data Index: 367655 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 4.5556. Min Range: -4.5556

Max Act: 3.9813. Min Act: -0.1700

Data Index: 5506989 (Open Web Text)

Max Activating Token Index: 26