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

Dataset: Open Web Text

Neuron 3062 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: 3.9957. Min Range: -3.9957

Max Act: 3.9957. Min Act: -0.1700

Data Index: 3219708 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.8917. Min Act: -0.1700

Data Index: 8151742 (Open Web Text)

Max Activating Token Index: 276

Text #2

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.8067. Min Act: -0.1700

Data Index: 1356551 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7983. Min Act: -0.1700

Data Index: 7922137 (Open Web Text)

Max Activating Token Index: 729

Text #4

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7790. Min Act: -0.1700

Data Index: 6999723 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7759. Min Act: -0.1700

Data Index: 7782597 (Open Web Text)

Max Activating Token Index: 196

Text #6

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7622. Min Act: -0.1700

Data Index: 5837389 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1122848 (Open Web Text)

Max Activating Token Index: 517

Text #8

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7219. Min Act: -0.1700

Data Index: 3603120 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.6993. Min Act: -0.1700

Data Index: 4413478 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7097. Min Act: -0.1700

Data Index: 3839325 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7073. Min Act: -0.1700

Data Index: 1503134 (Open Web Text)

Max Activating Token Index: 938

Text #12

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.6793. Min Act: -0.1700

Data Index: 2807552 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7276. Min Act: -0.1700

Data Index: 6353922 (Open Web Text)

Max Activating Token Index: 290

Text #14

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7284. Min Act: -0.1700

Data Index: 456488 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7276. Min Act: -0.1700

Data Index: 3798981 (Open Web Text)

Max Activating Token Index: 809

Text #16

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7233. Min Act: -0.1700

Data Index: 855374 (Open Web Text)

Max Activating Token Index: 609

Text #17

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.6947. Min Act: -0.1700

Data Index: 4567182 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.6669. Min Act: -0.1700

Data Index: 6452488 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 3.9957. Min Range: -3.9957

Max Act: 3.7011. Min Act: -0.1700

Data Index: 5268836 (Open Web Text)

Max Activating Token Index: 1021