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

Dataset: Open Web Text

Neuron 634 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: 4.1023. Min Range: -4.1023

Max Act: 4.1023. Min Act: -0.1700

Data Index: 1242479 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.8831. Min Act: -0.1700

Data Index: 7542204 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.8500. Min Act: -0.1700

Data Index: 3853333 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.8067. Min Act: -0.1700

Data Index: 8201210 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7912. Min Act: -0.1700

Data Index: 7669218 (Open Web Text)

Max Activating Token Index: 822

Text #5

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7797. Min Act: -0.1700

Data Index: 5947205 (Open Web Text)

Max Activating Token Index: 435

Text #6

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7974. Min Act: -0.1700

Data Index: 7124525 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7402. Min Act: -0.1700

Data Index: 1284694 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7535. Min Act: -0.1700

Data Index: 3558086 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7625. Min Act: -0.1700

Data Index: 1446265 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7788. Min Act: -0.1700

Data Index: 1671040 (Open Web Text)

Max Activating Token Index: 863

Text #11

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7184. Min Act: -0.1700

Data Index: 3175485 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.7050. Min Act: -0.1700

Data Index: 7837084 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6861. Min Act: -0.1700

Data Index: 6722890 (Open Web Text)

Max Activating Token Index: 922

Text #14

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6844. Min Act: -0.1700

Data Index: 543428 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6630. Min Act: -0.1700

Data Index: 5068911 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6982. Min Act: -0.1700

Data Index: 4595118 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6617. Min Act: -0.1700

Data Index: 5579691 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6665. Min Act: -0.1700

Data Index: 450110 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 4.1023. Min Range: -4.1023

Max Act: 3.6514. Min Act: -0.1700

Data Index: 5351722 (Open Web Text)

Max Activating Token Index: 48