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

Dataset: Open Web Text

Neuron 206 in Layer 1

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: 4.8727. Min Range: -4.8727

Max Act: 4.8572. Min Act: -0.1700

Data Index: 7560160 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.8727. Min Act: -0.1700

Data Index: 1531901 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.8386. Min Act: -0.1700

Data Index: 4864009 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7885. Min Act: -0.1700

Data Index: 3804187 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7630. Min Act: -0.1700

Data Index: 4070661 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7630. Min Act: -0.1700

Data Index: 1899116 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7353. Min Act: -0.1700

Data Index: 7316203 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7553. Min Act: -0.1700

Data Index: 5057574 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7371. Min Act: -0.1700

Data Index: 7977734 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7362. Min Act: -0.1700

Data Index: 2224414 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7090. Min Act: -0.1700

Data Index: 345750 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7242. Min Act: -0.1700

Data Index: 4938849 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7106. Min Act: -0.1700

Data Index: 7664261 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.6921. Min Act: -0.1700

Data Index: 3606044 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7201. Min Act: -0.1700

Data Index: 4032183 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.6997. Min Act: -0.1700

Data Index: 884284 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7134. Min Act: -0.1700

Data Index: 5110882 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.6986. Min Act: -0.1700

Data Index: 6614631 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.7105. Min Act: -0.1700

Data Index: 8237332 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.8727. Min Range: -4.8727

Max Act: 4.6875. Min Act: -0.1700

Data Index: 5842988 (Open Web Text)

Max Activating Token Index: 6