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

Dataset: Open Web Text

Neuron 1414 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: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1684

Data Index: 8816210 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1700

Data Index: 6047753 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1700

Data Index: 3931009 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1644

Data Index: 4775087 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5827. Min Act: -0.1699

Data Index: 3921929 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1700

Data Index: 1824523 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1659

Data Index: 8816202 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1698

Data Index: 5743613 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1671

Data Index: 1103492 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5792. Min Act: -0.1635

Data Index: 2217516 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5408. Min Act: -0.1700

Data Index: 3605803 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5408. Min Act: -0.1700

Data Index: 8562022 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5408. Min Act: -0.1700

Data Index: 8262438 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.5200. Min Act: -0.1700

Data Index: 2561154 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4881. Min Act: -0.1524

Data Index: 3601662 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4881. Min Act: -0.1613

Data Index: 5841262 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4918. Min Act: -0.1700

Data Index: 1166974 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4955. Min Act: -0.1700

Data Index: 6423254 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4754. Min Act: -0.1671

Data Index: 1642175 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.5827. Min Range: -5.5827

Max Act: 5.4728. Min Act: -0.1700

Data Index: 3172323 (Open Web Text)

Max Activating Token Index: 4