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

Dataset: Open Web Text

Neuron 2445 in Layer 2

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: 3.2646. Min Range: -3.2646

Max Act: 3.2646. Min Act: -0.1700

Data Index: 2695752 (Open Web Text)

Max Activating Token Index: 837

Text #1

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.2504. Min Act: -0.1700

Data Index: 1555957 (Open Web Text)

Max Activating Token Index: 792

Text #2

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.2570. Min Act: -0.1700

Data Index: 7696328 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.2389. Min Act: -0.1700

Data Index: 8412583 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1968. Min Act: -0.1700

Data Index: 912672 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1775. Min Act: -0.1700

Data Index: 1324835 (Open Web Text)

Max Activating Token Index: 88

Text #6

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1558. Min Act: -0.1700

Data Index: 2078520 (Open Web Text)

Max Activating Token Index: 175

Text #7

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1234. Min Act: -0.1700

Data Index: 5217850 (Open Web Text)

Max Activating Token Index: 534

Text #8

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1032. Min Act: -0.1700

Data Index: 8015041 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1022. Min Act: -0.1700

Data Index: 6827521 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.1096. Min Act: -0.1700

Data Index: 4972075 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0810. Min Act: -0.1700

Data Index: 986452 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0748. Min Act: -0.1700

Data Index: 1762225 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0806. Min Act: -0.1700

Data Index: 637015 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0641. Min Act: -0.1700

Data Index: 4792882 (Open Web Text)

Max Activating Token Index: 734

Text #15

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0582. Min Act: -0.1700

Data Index: 5434062 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0536. Min Act: -0.1700

Data Index: 2649428 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0596. Min Act: -0.1700

Data Index: 6331875 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0497. Min Act: -0.1700

Data Index: 4992770 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0417. Min Act: -0.1700

Data Index: 3450980 (Open Web Text)

Max Activating Token Index: 430