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

Dataset: Open Web Text

Neuron 485 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: 1.6061. Min Range: -1.6061

Max Act: 1.6061. Min Act: -0.1700

Data Index: 2641042 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5861. Min Act: -0.1693

Data Index: 5638904 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5973. Min Act: -0.1700

Data Index: 1305899 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5882. Min Act: -0.1700

Data Index: 777204 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5839. Min Act: -0.1691

Data Index: 4437660 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5472. Min Act: -0.1700

Data Index: 4358375 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5494. Min Act: -0.1700

Data Index: 7364427 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5404. Min Act: -0.1700

Data Index: 2460963 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5384. Min Act: -0.1699

Data Index: 1050806 (Open Web Text)

Max Activating Token Index: 901

Text #9

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5424. Min Act: -0.1700

Data Index: 8231410 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5303. Min Act: -0.1693

Data Index: 3059606 (Open Web Text)

Max Activating Token Index: 110

Text #11

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5259. Min Act: -0.1699

Data Index: 8432303 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5246. Min Act: -0.1700

Data Index: 4507298 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5049. Min Act: -0.1700

Data Index: 1581828 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5114. Min Act: -0.1700

Data Index: 5029864 (Open Web Text)

Max Activating Token Index: 362

Text #15

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5144. Min Act: -0.1700

Data Index: 1053529 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5193. Min Act: -0.1700

Data Index: 7810513 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5052. Min Act: -0.1698

Data Index: 6098603 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4950. Min Act: -0.1700

Data Index: 7196008 (Open Web Text)

Max Activating Token Index: 603

Text #19

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4992. Min Act: -0.1700

Data Index: 4128365 (Open Web Text)

Max Activating Token Index: 948