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

Dataset: Open Web Text

Neuron 2974 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: 1.8560. Min Range: -1.8560

Max Act: 1.8560. Min Act: -0.1695

Data Index: 4221151 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.8368. Min Act: -0.1696

Data Index: 8498645 (Open Web Text)

Max Activating Token Index: 844

Text #2

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.8306. Min Act: -0.1700

Data Index: 8504408 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.8087. Min Act: -0.1700

Data Index: 5077138 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.8071. Min Act: -0.1700

Data Index: 4775801 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.8069. Min Act: -0.1699

Data Index: 8389144 (Open Web Text)

Max Activating Token Index: 340

Text #6

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.8012. Min Act: -0.1700

Data Index: 8501160 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7934. Min Act: -0.1700

Data Index: 2029620 (Open Web Text)

Max Activating Token Index: 453

Text #8

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7964. Min Act: -0.1700

Data Index: 3104042 (Open Web Text)

Max Activating Token Index: 180

Text #9

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7845. Min Act: -0.1700

Data Index: 4106029 (Open Web Text)

Max Activating Token Index: 73

Text #10

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7861. Min Act: -0.1700

Data Index: 313523 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7840. Min Act: -0.1700

Data Index: 8299394 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7708. Min Act: -0.1700

Data Index: 1621897 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7800. Min Act: -0.1700

Data Index: 4380478 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7867. Min Act: -0.1700

Data Index: 919860 (Open Web Text)

Max Activating Token Index: 244

Text #15

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7889. Min Act: -0.1685

Data Index: 7256134 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7544. Min Act: -0.1697

Data Index: 6813305 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7630. Min Act: -0.1692

Data Index: 1790393 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7618. Min Act: -0.1700

Data Index: 5972495 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 1.8560. Min Range: -1.8560

Max Act: 1.7664. Min Act: -0.1700

Data Index: 81591 (Open Web Text)

Max Activating Token Index: 953