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

Dataset: Open Web Text

Neuron 1904 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: 5.0563. Min Range: -5.0563

Max Act: 5.0563. Min Act: -0.1700

Data Index: 8562451 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.0563. Min Range: -5.0563

Max Act: 5.0073. Min Act: -0.1700

Data Index: 8369206 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.0563. Min Range: -5.0563

Max Act: 5.0018. Min Act: -0.1699

Data Index: 3625040 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9740. Min Act: -0.1700

Data Index: 2956262 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9951. Min Act: -0.1700

Data Index: 2994869 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9684. Min Act: -0.1700

Data Index: 182781 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9823. Min Act: -0.1700

Data Index: 1771434 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9484. Min Act: -0.1700

Data Index: 5370723 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9481. Min Act: -0.1700

Data Index: 8471577 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9398. Min Act: -0.1700

Data Index: 7386001 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9603. Min Act: -0.1700

Data Index: 4353104 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9513. Min Act: -0.1700

Data Index: 6919387 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9488. Min Act: -0.1700

Data Index: 6713983 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9172. Min Act: -0.1700

Data Index: 7298036 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9063. Min Act: -0.1700

Data Index: 3928329 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9096. Min Act: -0.1700

Data Index: 6838754 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9295. Min Act: -0.1700

Data Index: 3398751 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9119. Min Act: -0.1700

Data Index: 949334 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9167. Min Act: -0.1700

Data Index: 5500670 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.0563. Min Range: -5.0563

Max Act: 4.9365. Min Act: -0.1700

Data Index: 3286576 (Open Web Text)

Max Activating Token Index: 6