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

Dataset: Open Web Text

Neuron 1467 in Layer 2

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: 3.2416. Min Range: -3.2416

Max Act: 3.2416. Min Act: -0.1700

Data Index: 8644927 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.1328. Min Act: -0.1700

Data Index: 8210960 (Open Web Text)

Max Activating Token Index: 714

Text #2

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0944. Min Act: -0.1700

Data Index: 8138708 (Open Web Text)

Max Activating Token Index: 694

Text #3

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0822. Min Act: -0.1700

Data Index: 4619087 (Open Web Text)

Max Activating Token Index: 783

Text #4

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0907. Min Act: -0.1700

Data Index: 5980567 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0654. Min Act: -0.1700

Data Index: 963526 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0826. Min Act: -0.1700

Data Index: 6167180 (Open Web Text)

Max Activating Token Index: 625

Text #7

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0569. Min Act: -0.1700

Data Index: 1686826 (Open Web Text)

Max Activating Token Index: 434

Text #8

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0542. Min Act: -0.1700

Data Index: 458410 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0411. Min Act: -0.1700

Data Index: 2287985 (Open Web Text)

Max Activating Token Index: 723

Text #10

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0608. Min Act: -0.1700

Data Index: 7265301 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0229. Min Act: -0.1700

Data Index: 1694644 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0423. Min Act: -0.1700

Data Index: 4512141 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0311. Min Act: -0.1700

Data Index: 4601561 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0180. Min Act: -0.1700

Data Index: 732965 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0187. Min Act: -0.1700

Data Index: 1148863 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0084. Min Act: -0.1700

Data Index: 4901657 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0130. Min Act: -0.1700

Data Index: 280893 (Open Web Text)

Max Activating Token Index: 715

Text #18

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0086. Min Act: -0.1700

Data Index: 5771082 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0072. Min Act: -0.1700

Data Index: 413125 (Open Web Text)

Max Activating Token Index: 122