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

Dataset: Open Web Text

Neuron 113 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: 3.7111. Min Range: -3.7111

Max Act: 3.7111. Min Act: -0.1700

Data Index: 170108 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6757. Min Act: -0.1700

Data Index: 262996 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6369. Min Act: -0.1700

Data Index: 1227140 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6313. Min Act: -0.1700

Data Index: 7080789 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6229. Min Act: -0.1700

Data Index: 922146 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6149. Min Act: -0.1700

Data Index: 3335105 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6070. Min Act: -0.1700

Data Index: 8707973 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5900. Min Act: -0.1700

Data Index: 7063645 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5802. Min Act: -0.1700

Data Index: 5243543 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6015. Min Act: -0.1700

Data Index: 2783268 (Open Web Text)

Max Activating Token Index: 76

Text #10

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5851. Min Act: -0.1700

Data Index: 645628 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5880. Min Act: -0.1700

Data Index: 8454347 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5859. Min Act: -0.1700

Data Index: 8511803 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5546. Min Act: -0.1700

Data Index: 7776366 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5443. Min Act: -0.1700

Data Index: 3451830 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5795. Min Act: -0.1700

Data Index: 3343287 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5588. Min Act: -0.1700

Data Index: 5655018 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5538. Min Act: -0.1700

Data Index: 5363482 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5551. Min Act: -0.1700

Data Index: 3018741 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5187. Min Act: -0.1700

Data Index: 2876831 (Open Web Text)

Max Activating Token Index: 19