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

Dataset: Open Web Text

Neuron 2242 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: 1.9227. Min Range: -1.9227

Max Act: 1.9227. Min Act: -0.1698

Data Index: 7632391 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.8547. Min Act: -0.1700

Data Index: 3203789 (Open Web Text)

Max Activating Token Index: 461

Text #2

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.8559. Min Act: -0.1700

Data Index: 8262411 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.8506. Min Act: -0.1700

Data Index: 3607733 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.8446. Min Act: -0.1700

Data Index: 3795962 (Open Web Text)

Max Activating Token Index: 764

Text #5

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.8389. Min Act: -0.1700

Data Index: 2445522 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7978. Min Act: -0.1700

Data Index: 8740198 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7888. Min Act: -0.1700

Data Index: 1255970 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7386. Min Act: -0.1700

Data Index: 61178 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7348. Min Act: -0.1700

Data Index: 2800590 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7333. Min Act: -0.1700

Data Index: 594520 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7364. Min Act: -0.1700

Data Index: 7017688 (Open Web Text)

Max Activating Token Index: 502

Text #12

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7260. Min Act: -0.1700

Data Index: 2791654 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7260. Min Act: -0.1700

Data Index: 3910412 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7260. Min Act: -0.1699

Data Index: 1914098 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.7001. Min Act: -0.1700

Data Index: 7660894 (Open Web Text)

Max Activating Token Index: 110

Text #16

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.6992. Min Act: -0.1700

Data Index: 7053309 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.6875. Min Act: -0.1698

Data Index: 2352516 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.6993. Min Act: -0.1700

Data Index: 1607780 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 1.9227. Min Range: -1.9227

Max Act: 1.6986. Min Act: -0.1700

Data Index: 7903160 (Open Web Text)

Max Activating Token Index: 12