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

Dataset: Open Web Text

Neuron 1830 in Layer 2

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: 1.8825. Min Range: -1.8825

Max Act: 1.8825. Min Act: -0.1700

Data Index: 1767046 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.8294. Min Act: -0.1700

Data Index: 6995765 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.8148. Min Act: -0.1700

Data Index: 2522429 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.8205. Min Act: -0.1700

Data Index: 7424380 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7955. Min Act: -0.1700

Data Index: 4392482 (Open Web Text)

Max Activating Token Index: 177

Text #5

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7906. Min Act: -0.1700

Data Index: 8646233 (Open Web Text)

Max Activating Token Index: 87

Text #6

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7756. Min Act: -0.1700

Data Index: 3138086 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7490. Min Act: -0.1700

Data Index: 2003550 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7321. Min Act: -0.1700

Data Index: 3332738 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7236. Min Act: -0.1700

Data Index: 4859146 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.7017. Min Act: -0.1700

Data Index: 5114531 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6909. Min Act: -0.1700

Data Index: 98000 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6971. Min Act: -0.1700

Data Index: 4089551 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6937. Min Act: -0.1700

Data Index: 1057977 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6933. Min Act: -0.1700

Data Index: 5091801 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6849. Min Act: -0.1700

Data Index: 8002325 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6817. Min Act: -0.1700

Data Index: 2665654 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6687. Min Act: -0.1700

Data Index: 5114560 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6714. Min Act: -0.1700

Data Index: 701322 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 1.8825. Min Range: -1.8825

Max Act: 1.6615. Min Act: -0.1700

Data Index: 6174501 (Open Web Text)

Max Activating Token Index: 228