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

Dataset: Open Web Text

Neuron 2461 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: 1.7567. Min Range: -1.7567

Max Act: 1.7567. Min Act: -0.1700

Data Index: 2951808 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7406. Min Act: -0.1700

Data Index: 5915003 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7234. Min Act: -0.1700

Data Index: 5449212 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7159. Min Act: -0.1683

Data Index: 5573902 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7116. Min Act: -0.1700

Data Index: 4443400 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7076. Min Act: -0.1700

Data Index: 2520237 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.7072. Min Act: -0.1700

Data Index: 5539349 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6903. Min Act: -0.1700

Data Index: 3159176 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6807. Min Act: -0.1700

Data Index: 3816932 (Open Web Text)

Max Activating Token Index: 681

Text #9

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6847. Min Act: -0.1700

Data Index: 7871411 (Open Web Text)

Max Activating Token Index: 415

Text #10

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6881. Min Act: -0.1700

Data Index: 6406710 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6777. Min Act: -0.1700

Data Index: 3141047 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6666. Min Act: -0.1700

Data Index: 7613860 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6532. Min Act: -0.1700

Data Index: 4067743 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6482. Min Act: -0.1700

Data Index: 8664974 (Open Web Text)

Max Activating Token Index: 911

Text #15

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6587. Min Act: -0.1700

Data Index: 8431709 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6398. Min Act: -0.1700

Data Index: 1309378 (Open Web Text)

Max Activating Token Index: 657

Text #17

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6581. Min Act: -0.1700

Data Index: 3816929 (Open Web Text)

Max Activating Token Index: 976

Text #18

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6511. Min Act: -0.1700

Data Index: 3005802 (Open Web Text)

Max Activating Token Index: 1008

Text #19

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6410. Min Act: -0.1700

Data Index: 1684661 (Open Web Text)

Max Activating Token Index: 140