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

Dataset: Open Web Text

Neuron 1944 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: 3.6997. Min Range: -3.6997

Max Act: 3.6997. Min Act: -0.1700

Data Index: 1175362 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6494. Min Act: -0.1700

Data Index: 5797869 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6546. Min Act: -0.1700

Data Index: 7305818 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6588. Min Act: -0.1700

Data Index: 6856745 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6456. Min Act: -0.1700

Data Index: 1908846 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6076. Min Act: -0.1700

Data Index: 3870563 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6064. Min Act: -0.1700

Data Index: 8403089 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5919. Min Act: -0.1700

Data Index: 214408 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6165. Min Act: -0.1700

Data Index: 2213902 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6011. Min Act: -0.1700

Data Index: 1061535 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5997. Min Act: -0.1700

Data Index: 6045023 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5628. Min Act: -0.1700

Data Index: 3947724 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5804. Min Act: -0.1700

Data Index: 274263 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5860. Min Act: -0.1700

Data Index: 7851743 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5821. Min Act: -0.1700

Data Index: 1456175 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5785. Min Act: -0.1700

Data Index: 5453022 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5658. Min Act: -0.1700

Data Index: 40660 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1873519 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5445. Min Act: -0.1700

Data Index: 3381247 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5462. Min Act: -0.1700

Data Index: 5827826 (Open Web Text)

Max Activating Token Index: 7