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

Dataset: Open Web Text

Neuron 547 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: 2.8033. Min Range: -2.8033

Max Act: 2.7909. Min Act: -0.1700

Data Index: 6727600 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7914. Min Act: -0.1700

Data Index: 650388 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7909. Min Act: -0.1700

Data Index: 6727599 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.8033. Min Act: -0.1700

Data Index: 2807541 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7823. Min Act: -0.1700

Data Index: 3093496 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7573. Min Act: -0.1700

Data Index: 8366484 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7582. Min Act: -0.1700

Data Index: 4704418 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7751. Min Act: -0.1700

Data Index: 7505693 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7701. Min Act: -0.1700

Data Index: 3249873 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7480. Min Act: -0.1700

Data Index: 4266130 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7425. Min Act: -0.1700

Data Index: 4489910 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7530. Min Act: -0.1700

Data Index: 4160722 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7443. Min Act: -0.1700

Data Index: 2297971 (Open Web Text)

Max Activating Token Index: 794

Text #13

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7506. Min Act: -0.1700

Data Index: 41005 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7530. Min Act: -0.1700

Data Index: 1955250 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7506. Min Act: -0.1700

Data Index: 5442262 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7262. Min Act: -0.1700

Data Index: 5252009 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7412. Min Act: -0.1700

Data Index: 5442016 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7404. Min Act: -0.1700

Data Index: 2112717 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8033. Min Range: -2.8033

Max Act: 2.7378. Min Act: -0.1700

Data Index: 5502215 (Open Web Text)

Max Activating Token Index: 5