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

Dataset: Open Web Text

Neuron 1372 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: 6.5477. Min Range: -6.5477

Max Act: 6.5477. Min Act: -0.1700

Data Index: 1630313 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.3374. Min Act: -0.1700

Data Index: 5699068 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.2466. Min Act: -0.1700

Data Index: 1922358 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.2567. Min Act: -0.1700

Data Index: 1633067 (Open Web Text)

Max Activating Token Index: 882

Text #4

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.2002. Min Act: -0.1700

Data Index: 5017648 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.1590. Min Act: -0.1700

Data Index: 2962339 (Open Web Text)

Max Activating Token Index: 896

Text #6

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.2064. Min Act: -0.1700

Data Index: 6842086 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0932. Min Act: -0.1700

Data Index: 6126379 (Open Web Text)

Max Activating Token Index: 269

Text #8

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.1551. Min Act: -0.1700

Data Index: 8615099 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0988. Min Act: -0.1700

Data Index: 8310915 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0769. Min Act: -0.1700

Data Index: 5431946 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0123. Min Act: -0.1700

Data Index: 6800366 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0534. Min Act: -0.1700

Data Index: 4765882 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 6.5477. Min Range: -6.5477

Max Act: 5.9964. Min Act: -0.1700

Data Index: 173176 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0047. Min Act: -0.1700

Data Index: 5413150 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0173. Min Act: -0.1700

Data Index: 5263735 (Open Web Text)

Max Activating Token Index: 857

Text #16

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0265. Min Act: -0.1700

Data Index: 660333 (Open Web Text)

Max Activating Token Index: 51

Text #17

Max Range: 6.5477. Min Range: -6.5477

Max Act: 5.9842. Min Act: -0.1700

Data Index: 3826375 (Open Web Text)

Max Activating Token Index: 116

Text #18

Max Range: 6.5477. Min Range: -6.5477

Max Act: 6.0352. Min Act: -0.1700

Data Index: 6458332 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 6.5477. Min Range: -6.5477

Max Act: 5.9974. Min Act: -0.1700

Data Index: 3730488 (Open Web Text)

Max Activating Token Index: 209