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

Dataset: Open Web Text

Neuron 2560 in Layer 0

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: 4.0667. Min Range: -4.0667

Max Act: 4.0667. Min Act: -0.1700

Data Index: 5192067 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0205. Min Act: -0.1700

Data Index: 5604470 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0232. Min Act: -0.1700

Data Index: 3141965 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0017. Min Act: -0.1700

Data Index: 1862567 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0072. Min Act: -0.1700

Data Index: 1568966 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9954. Min Act: -0.1700

Data Index: 4168377 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9797. Min Act: -0.1700

Data Index: 8255559 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0084. Min Act: -0.1700

Data Index: 456165 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9969. Min Act: -0.1700

Data Index: 6106936 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9784. Min Act: -0.1700

Data Index: 3674915 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9696. Min Act: -0.1700

Data Index: 2434428 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9631. Min Act: -0.1700

Data Index: 1312145 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9523. Min Act: -0.1700

Data Index: 5271280 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9665. Min Act: -0.1700

Data Index: 5494983 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9730. Min Act: -0.1700

Data Index: 373662 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9802. Min Act: -0.1700

Data Index: 1727616 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9517. Min Act: -0.1700

Data Index: 1261808 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9331. Min Act: -0.1700

Data Index: 1930264 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9543. Min Act: -0.1700

Data Index: 5585178 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9238. Min Act: -0.1700

Data Index: 1763969 (Open Web Text)

Max Activating Token Index: 8