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

Dataset: Open Web Text

Neuron 2201 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: 1.8727. Min Range: -1.8727

Max Act: 1.8727. Min Act: -0.1700

Data Index: 5953595 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8334. Min Act: -0.1700

Data Index: 5961990 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8182. Min Act: -0.1700

Data Index: 3747630 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8014. Min Act: -0.1700

Data Index: 3421405 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8063. Min Act: -0.1700

Data Index: 2034801 (Open Web Text)

Max Activating Token Index: 303

Text #5

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8037. Min Act: -0.1700

Data Index: 6619366 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8044. Min Act: -0.1700

Data Index: 7066516 (Open Web Text)

Max Activating Token Index: 390

Text #7

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8110. Min Act: -0.1700

Data Index: 2429238 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7983. Min Act: -0.1700

Data Index: 1756573 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7987. Min Act: -0.1700

Data Index: 1812838 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7761. Min Act: -0.1700

Data Index: 310266 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7801. Min Act: -0.1700

Data Index: 4232898 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7795. Min Act: -0.1700

Data Index: 7464782 (Open Web Text)

Max Activating Token Index: 282

Text #13

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7661. Min Act: -0.1700

Data Index: 3774860 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7616. Min Act: -0.1700

Data Index: 1621712 (Open Web Text)

Max Activating Token Index: 694

Text #15

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7653. Min Act: -0.1700

Data Index: 5150176 (Open Web Text)

Max Activating Token Index: 662

Text #16

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7839. Min Act: -0.1700

Data Index: 61216 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7753. Min Act: -0.1700

Data Index: 2707036 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7639. Min Act: -0.1700

Data Index: 5185324 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.7730. Min Act: -0.1700

Data Index: 5579301 (Open Web Text)

Max Activating Token Index: 504