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

Dataset: Open Web Text

Neuron 1657 in Layer 3

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: 3.9519. Min Range: -3.9519

Max Act: 3.9473. Min Act: -0.1700

Data Index: 4552791 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.9519. Min Act: -0.1700

Data Index: 1853898 (Open Web Text)

Max Activating Token Index: 702

Text #2

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.9235. Min Act: -0.1700

Data Index: 3732429 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.9141. Min Act: -0.1700

Data Index: 2681836 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8837. Min Act: -0.1700

Data Index: 1455040 (Open Web Text)

Max Activating Token Index: 325

Text #5

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.9064. Min Act: -0.1700

Data Index: 6554000 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8950. Min Act: -0.1700

Data Index: 1920558 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8878. Min Act: -0.1700

Data Index: 4340052 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8623. Min Act: -0.1700

Data Index: 2962497 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8590. Min Act: -0.1700

Data Index: 658011 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8667. Min Act: -0.1700

Data Index: 4033341 (Open Web Text)

Max Activating Token Index: 932

Text #11

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8624. Min Act: -0.1700

Data Index: 4246175 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8344. Min Act: -0.1700

Data Index: 7948567 (Open Web Text)

Max Activating Token Index: 879

Text #13

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8320. Min Act: -0.1700

Data Index: 7892811 (Open Web Text)

Max Activating Token Index: 562

Text #14

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8594. Min Act: -0.1700

Data Index: 3557930 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8417. Min Act: -0.1700

Data Index: 7197416 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8357. Min Act: -0.1700

Data Index: 5731270 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8257. Min Act: -0.1700

Data Index: 3769795 (Open Web Text)

Max Activating Token Index: 409

Text #18

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7914. Min Act: -0.1700

Data Index: 929299 (Open Web Text)

Max Activating Token Index: 557

Text #19

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7593. Min Act: -0.1700

Data Index: 7149078 (Open Web Text)

Max Activating Token Index: 1019