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

Dataset: Open Web Text

Neuron 2409 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: 3.1035. Min Range: -3.1035

Max Act: 3.1035. Min Act: -0.1700

Data Index: 8250244 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9671. Min Act: -0.1700

Data Index: 7223786 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9572. Min Act: -0.1700

Data Index: 968431 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9435. Min Act: -0.1700

Data Index: 1120630 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9386. Min Act: -0.1700

Data Index: 5068735 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9298. Min Act: -0.1700

Data Index: 7949113 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9351. Min Act: -0.1700

Data Index: 8529562 (Open Web Text)

Max Activating Token Index: 658

Text #7

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9298. Min Act: -0.1700

Data Index: 6328739 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9153. Min Act: -0.1700

Data Index: 7363785 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.9142. Min Act: -0.1700

Data Index: 3172822 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8922. Min Act: -0.1700

Data Index: 3061819 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8815. Min Act: -0.1700

Data Index: 1477040 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8783. Min Act: -0.1700

Data Index: 3957600 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8360. Min Act: -0.1700

Data Index: 8516000 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8189. Min Act: -0.1700

Data Index: 2819584 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8227. Min Act: -0.1700

Data Index: 5824360 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8313. Min Act: -0.1700

Data Index: 2784562 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.7891. Min Act: -0.1700

Data Index: 1945151 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.8083. Min Act: -0.1700

Data Index: 1724579 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.7889. Min Act: -0.1700

Data Index: 468628 (Open Web Text)

Max Activating Token Index: 3