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

Dataset: Open Web Text

Neuron 2433 in Layer 3

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: 4.2720. Min Range: -4.2720

Max Act: 4.2720. Min Act: -0.1700

Data Index: 1216875 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.2720. Min Act: -0.1700

Data Index: 114693 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.2357. Min Act: -0.1700

Data Index: 3257809 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.1561. Min Act: -0.1700

Data Index: 8305843 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.1294. Min Act: -0.1700

Data Index: 8419159 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.1373. Min Act: -0.1700

Data Index: 2186852 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.1439. Min Act: -0.1700

Data Index: 3494695 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.0644. Min Act: -0.1700

Data Index: 932523 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.0520. Min Act: -0.1700

Data Index: 8421773 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.0520. Min Act: -0.1700

Data Index: 4729111 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.0227. Min Act: -0.1700

Data Index: 8305842 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.0261. Min Act: -0.1700

Data Index: 7030867 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.2720. Min Range: -4.2720

Max Act: 4.0066. Min Act: -0.1700

Data Index: 8153588 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9919. Min Act: -0.1700

Data Index: 6388088 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9632. Min Act: -0.1700

Data Index: 712115 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9919. Min Act: -0.1700

Data Index: 7204242 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9632. Min Act: -0.1700

Data Index: 6664143 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9578. Min Act: -0.1700

Data Index: 7725106 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9919. Min Act: -0.1700

Data Index: 3494178 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.2720. Min Range: -4.2720

Max Act: 3.9632. Min Act: -0.1700

Data Index: 865494 (Open Web Text)

Max Activating Token Index: 4