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

Dataset: Open Web Text

Neuron 1752 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: 4.0828. Min Range: -4.0828

Max Act: 4.0677. Min Act: -0.1700

Data Index: 8564576 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0828. Min Act: -0.1700

Data Index: 1160136 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0423. Min Act: -0.1700

Data Index: 2635646 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0469. Min Act: -0.1700

Data Index: 8658224 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0096. Min Act: -0.1700

Data Index: 7524439 (Open Web Text)

Max Activating Token Index: 241

Text #5

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0056. Min Act: -0.1700

Data Index: 3434126 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0013. Min Act: -0.1700

Data Index: 1654328 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0063. Min Act: -0.1700

Data Index: 1595996 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9985. Min Act: -0.1700

Data Index: 1091536 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9943. Min Act: -0.1700

Data Index: 2682626 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9973. Min Act: -0.1700

Data Index: 626281 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0150. Min Act: -0.1700

Data Index: 4794822 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9965. Min Act: -0.1700

Data Index: 8051800 (Open Web Text)

Max Activating Token Index: 1009

Text #13

Max Range: 4.0828. Min Range: -4.0828

Max Act: 4.0007. Min Act: -0.1700

Data Index: 145820 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9519. Min Act: -0.1700

Data Index: 4885918 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9580. Min Act: -0.1700

Data Index: 1424534 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9681. Min Act: -0.1700

Data Index: 6127081 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9631. Min Act: -0.1700

Data Index: 1479101 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9635. Min Act: -0.1700

Data Index: 3149883 (Open Web Text)

Max Activating Token Index: 58

Text #19

Max Range: 4.0828. Min Range: -4.0828

Max Act: 3.9639. Min Act: -0.1700

Data Index: 6254843 (Open Web Text)

Max Activating Token Index: 6