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

Dataset: Open Web Text

Neuron 1428 in Layer 3

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: 4.0502. Min Range: -4.0502

Max Act: 4.0502. Min Act: -0.1700

Data Index: 1913017 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.9781. Min Act: -0.1700

Data Index: 1359650 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.9018. Min Act: -0.1700

Data Index: 8143968 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8688. Min Act: -0.1700

Data Index: 4816803 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8578. Min Act: -0.1700

Data Index: 2612370 (Open Web Text)

Max Activating Token Index: 198

Text #5

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8914. Min Act: -0.1700

Data Index: 3750907 (Open Web Text)

Max Activating Token Index: 713

Text #6

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8887. Min Act: -0.1700

Data Index: 8738932 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8242. Min Act: -0.1700

Data Index: 3218515 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8958. Min Act: -0.1700

Data Index: 5332560 (Open Web Text)

Max Activating Token Index: 937

Text #9

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8482. Min Act: -0.1700

Data Index: 1140827 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8528. Min Act: -0.1700

Data Index: 4318324 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8557. Min Act: -0.1700

Data Index: 4275815 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8401. Min Act: -0.1700

Data Index: 1617865 (Open Web Text)

Max Activating Token Index: 145

Text #13

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8323. Min Act: -0.1700

Data Index: 8751240 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8464. Min Act: -0.1700

Data Index: 5828632 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8623. Min Act: -0.1700

Data Index: 1433767 (Open Web Text)

Max Activating Token Index: 513

Text #16

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8840. Min Act: -0.1700

Data Index: 5031626 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8216. Min Act: -0.1700

Data Index: 1719079 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8951. Min Act: -0.1700

Data Index: 8019642 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 4.0502. Min Range: -4.0502

Max Act: 3.8036. Min Act: -0.1700

Data Index: 4356427 (Open Web Text)

Max Activating Token Index: 374