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

Dataset: Open Web Text

Neuron 2068 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: 2.7606. Min Range: -2.7606

Max Act: 2.7606. Min Act: -0.1700

Data Index: 3578455 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7298. Min Act: -0.1700

Data Index: 1666412 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7317. Min Act: -0.1700

Data Index: 7233767 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 186388 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 5973624 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 1612859 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 1527154 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 5913903 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7261. Min Act: -0.1700

Data Index: 5684604 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 7302660 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 1397281 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 7194796 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 6198667 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.7044. Min Act: -0.1700

Data Index: 6018445 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.6999. Min Act: -0.1700

Data Index: 8797810 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.6799. Min Act: -0.1700

Data Index: 1518273 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.6799. Min Act: -0.1700

Data Index: 4558324 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.6880. Min Act: -0.1700

Data Index: 6004027 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.6799. Min Act: -0.1700

Data Index: 360537 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.7606. Min Range: -2.7606

Max Act: 2.6799. Min Act: -0.1700

Data Index: 4981493 (Open Web Text)

Max Activating Token Index: 2