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

Dataset: Open Web Text

Neuron 2023 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: 6.5221. Min Range: -6.5221

Max Act: 6.5221. Min Act: -0.1700

Data Index: 6127409 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4853. Min Act: -0.1700

Data Index: 3120680 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4885. Min Act: -0.1700

Data Index: 1236036 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4895. Min Act: -0.1700

Data Index: 4192187 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4529. Min Act: -0.1700

Data Index: 1720505 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4477. Min Act: -0.1700

Data Index: 8440203 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4361. Min Act: -0.1700

Data Index: 6641554 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4143. Min Act: -0.1700

Data Index: 6420613 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4093. Min Act: -0.1700

Data Index: 6932658 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4329. Min Act: -0.1700

Data Index: 6714308 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4154. Min Act: -0.1700

Data Index: 1958634 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.4010. Min Act: -0.1700

Data Index: 7249905 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3849. Min Act: -0.1700

Data Index: 6986510 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3688. Min Act: -0.1700

Data Index: 6685595 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3690. Min Act: -0.1700

Data Index: 2667066 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3765. Min Act: -0.1700

Data Index: 7820071 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3724. Min Act: -0.1700

Data Index: 6944481 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3610. Min Act: -0.1700

Data Index: 2534973 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3654. Min Act: -0.1700

Data Index: 24385 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 6.5221. Min Range: -6.5221

Max Act: 6.3526. Min Act: -0.1700

Data Index: 1569840 (Open Web Text)

Max Activating Token Index: 16