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

Dataset: Open Web Text

Neuron 982 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: 4.6578. Min Range: -4.6578

Max Act: 4.6578. Min Act: -0.1700

Data Index: 3451024 (Open Web Text)

Max Activating Token Index: 275

Text #1

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.6299. Min Act: -0.1700

Data Index: 3549548 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5912. Min Act: -0.1700

Data Index: 854548 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5881. Min Act: -0.1700

Data Index: 3369073 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5317. Min Act: -0.1700

Data Index: 2204617 (Open Web Text)

Max Activating Token Index: 489

Text #5

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5542. Min Act: -0.1700

Data Index: 8653522 (Open Web Text)

Max Activating Token Index: 796

Text #6

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5641. Min Act: -0.1700

Data Index: 2896465 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5465. Min Act: -0.1700

Data Index: 1539764 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5633. Min Act: -0.1700

Data Index: 3529079 (Open Web Text)

Max Activating Token Index: 305

Text #9

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.4991. Min Act: -0.1700

Data Index: 3951854 (Open Web Text)

Max Activating Token Index: 978

Text #10

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5254. Min Act: -0.1700

Data Index: 2013300 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5374. Min Act: -0.1700

Data Index: 7140407 (Open Web Text)

Max Activating Token Index: 460

Text #12

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5676. Min Act: -0.1700

Data Index: 1794751 (Open Web Text)

Max Activating Token Index: 799

Text #13

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5015. Min Act: -0.1700

Data Index: 2518814 (Open Web Text)

Max Activating Token Index: 644

Text #14

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.4487. Min Act: -0.1700

Data Index: 473539 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.4670. Min Act: -0.1700

Data Index: 7115107 (Open Web Text)

Max Activating Token Index: 566

Text #16

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.4803. Min Act: -0.1700

Data Index: 6912153 (Open Web Text)

Max Activating Token Index: 856

Text #17

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5076. Min Act: -0.1700

Data Index: 7136834 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.5005. Min Act: -0.1700

Data Index: 6495846 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 4.6578. Min Range: -4.6578

Max Act: 4.4967. Min Act: -0.1700

Data Index: 3564282 (Open Web Text)

Max Activating Token Index: 32