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

Dataset: Open Web Text

Neuron 3020 in Layer 6

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: 3.9012. Min Range: -3.9012

Max Act: 3.9012. Min Act: -0.1700

Data Index: 505136 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.7826. Min Act: -0.1700

Data Index: 5047830 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.7496. Min Act: -0.1700

Data Index: 8417956 (Open Web Text)

Max Activating Token Index: 751

Text #3

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.7446. Min Act: -0.1700

Data Index: 6550695 (Open Web Text)

Max Activating Token Index: 191

Text #4

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.7298. Min Act: -0.1700

Data Index: 989465 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6786. Min Act: -0.1700

Data Index: 5808746 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6749. Min Act: -0.1700

Data Index: 1317731 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6824. Min Act: -0.1700

Data Index: 290708 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6409. Min Act: -0.1700

Data Index: 6110550 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6214. Min Act: -0.1700

Data Index: 2330810 (Open Web Text)

Max Activating Token Index: 519

Text #10

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6375. Min Act: -0.1700

Data Index: 3228580 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.5858. Min Act: -0.1700

Data Index: 5973661 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6243. Min Act: -0.1700

Data Index: 5095247 (Open Web Text)

Max Activating Token Index: 634

Text #13

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6349. Min Act: -0.1700

Data Index: 3017589 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6343. Min Act: -0.1700

Data Index: 3201775 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6048. Min Act: -0.1700

Data Index: 8510136 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.6098. Min Act: -0.1700

Data Index: 5596074 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.5948. Min Act: -0.1700

Data Index: 8273437 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.5914. Min Act: -0.1700

Data Index: 827800 (Open Web Text)

Max Activating Token Index: 884

Text #19

Max Range: 3.9012. Min Range: -3.9012

Max Act: 3.5865. Min Act: -0.1700

Data Index: 7023531 (Open Web Text)

Max Activating Token Index: 673