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

Dataset: Open Web Text

Neuron 55 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: 2.2542. Min Range: -2.2542

Max Act: 2.2542. Min Act: -0.1700

Data Index: 2730774 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.2060. Min Act: -0.1700

Data Index: 8660446 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1734. Min Act: -0.1700

Data Index: 5955176 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1719. Min Act: -0.1700

Data Index: 7576496 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1567. Min Act: -0.1700

Data Index: 631300 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1448. Min Act: -0.1700

Data Index: 4054449 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1574. Min Act: -0.1700

Data Index: 8674936 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1517. Min Act: -0.1700

Data Index: 3409901 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1172. Min Act: -0.1700

Data Index: 8448020 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1082. Min Act: -0.1700

Data Index: 3494699 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1168. Min Act: -0.1700

Data Index: 4791087 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1027. Min Act: -0.1700

Data Index: 3458567 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.1069. Min Act: -0.1700

Data Index: 6449852 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0995. Min Act: -0.1700

Data Index: 487574 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0882. Min Act: -0.1700

Data Index: 2052767 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0811. Min Act: -0.1700

Data Index: 671642 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0849. Min Act: -0.1700

Data Index: 2159170 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0723. Min Act: -0.1700

Data Index: 7070894 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0777. Min Act: -0.1700

Data Index: 5618043 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 2.2542. Min Range: -2.2542

Max Act: 2.0677. Min Act: -0.1700

Data Index: 5766176 (Open Web Text)

Max Activating Token Index: 29