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

Dataset: Open Web Text

Neuron 1313 in Layer 1

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: 4.1669. Min Range: -4.1669

Max Act: 4.1588. Min Act: -0.1700

Data Index: 990897 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1559. Min Act: -0.1700

Data Index: 3357101 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1669. Min Act: -0.1700

Data Index: 1583118 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1297. Min Act: -0.1700

Data Index: 4885711 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1331. Min Act: -0.1700

Data Index: 1460768 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1332. Min Act: -0.1700

Data Index: 500293 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1494. Min Act: -0.1700

Data Index: 7073435 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1083. Min Act: -0.1700

Data Index: 554145 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1025. Min Act: -0.1700

Data Index: 4428476 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1165. Min Act: -0.1700

Data Index: 841532 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1162. Min Act: -0.1700

Data Index: 8217160 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1059. Min Act: -0.1700

Data Index: 1206914 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1253. Min Act: -0.1700

Data Index: 6129183 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1132. Min Act: -0.1700

Data Index: 2642692 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.1076. Min Act: -0.1700

Data Index: 5238679 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.0721. Min Act: -0.1700

Data Index: 1230643 (Open Web Text)

Max Activating Token Index: 88

Text #16

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.0907. Min Act: -0.1700

Data Index: 3844328 (Open Web Text)

Max Activating Token Index: 144

Text #17

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.0615. Min Act: -0.1700

Data Index: 4464817 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.0684. Min Act: -0.1700

Data Index: 511159 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 4.1669. Min Range: -4.1669

Max Act: 4.0581. Min Act: -0.1700

Data Index: 4780393 (Open Web Text)

Max Activating Token Index: 8