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

Dataset: Open Web Text

Neuron 451 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: 1.8738. Min Range: -1.8738

Max Act: 1.8738. Min Act: -0.1697

Data Index: 7754222 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8313. Min Act: -0.1700

Data Index: 8735368 (Open Web Text)

Max Activating Token Index: 38

Text #2

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8361. Min Act: -0.1699

Data Index: 1042644 (Open Web Text)

Max Activating Token Index: 191

Text #3

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8325. Min Act: -0.1698

Data Index: 4710846 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8277. Min Act: -0.1699

Data Index: 8167468 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8252. Min Act: -0.1700

Data Index: 8250754 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8160. Min Act: -0.1700

Data Index: 210046 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8186. Min Act: -0.1696

Data Index: 2808501 (Open Web Text)

Max Activating Token Index: 942

Text #8

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8234. Min Act: -0.1700

Data Index: 4859543 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8096. Min Act: -0.1700

Data Index: 740905 (Open Web Text)

Max Activating Token Index: 753

Text #10

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8062. Min Act: -0.1646

Data Index: 1687309 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8055. Min Act: -0.1700

Data Index: 1824217 (Open Web Text)

Max Activating Token Index: 538

Text #12

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8143. Min Act: -0.1699

Data Index: 8123028 (Open Web Text)

Max Activating Token Index: 969

Text #13

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.7944. Min Act: -0.1700

Data Index: 5674628 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8021. Min Act: -0.1700

Data Index: 6329714 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.8092. Min Act: -0.1700

Data Index: 7844014 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.7889. Min Act: -0.1700

Data Index: 3714986 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.7916. Min Act: -0.1700

Data Index: 5347600 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.7905. Min Act: -0.1700

Data Index: 5108991 (Open Web Text)

Max Activating Token Index: 135

Text #19

Max Range: 1.8738. Min Range: -1.8738

Max Act: 1.7895. Min Act: -0.1700

Data Index: 1601357 (Open Web Text)

Max Activating Token Index: 131