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

Dataset: Open Web Text

Neuron 279 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: 4.0173. Min Range: -4.0173

Max Act: 4.0132. Min Act: -0.1700

Data Index: 7199193 (Open Web Text)

Max Activating Token Index: 795

Text #1

Max Range: 4.0173. Min Range: -4.0173

Max Act: 4.0173. Min Act: -0.1700

Data Index: 7199201 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.9908. Min Act: -0.1700

Data Index: 8076501 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.9765. Min Act: -0.1700

Data Index: 5124533 (Open Web Text)

Max Activating Token Index: 250

Text #4

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.9737. Min Act: -0.1700

Data Index: 2752325 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.9111. Min Act: -0.1700

Data Index: 6029940 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.9044. Min Act: -0.1700

Data Index: 5719687 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.8981. Min Act: -0.1700

Data Index: 2752322 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.9032. Min Act: -0.1700

Data Index: 8601021 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.8941. Min Act: -0.1700

Data Index: 8234957 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.8458. Min Act: -0.1700

Data Index: 531322 (Open Web Text)

Max Activating Token Index: 806

Text #11

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.8044. Min Act: -0.1700

Data Index: 5147510 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.8100. Min Act: -0.1700

Data Index: 7565004 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7990. Min Act: -0.1700

Data Index: 4337751 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7323. Min Act: -0.1700

Data Index: 7778493 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7684. Min Act: -0.1700

Data Index: 5730815 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7685. Min Act: -0.1700

Data Index: 702931 (Open Web Text)

Max Activating Token Index: 387

Text #17

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7625. Min Act: -0.1700

Data Index: 3773670 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7624. Min Act: -0.1700

Data Index: 6708018 (Open Web Text)

Max Activating Token Index: 952

Text #19

Max Range: 4.0173. Min Range: -4.0173

Max Act: 3.7491. Min Act: -0.1700

Data Index: 2060873 (Open Web Text)

Max Activating Token Index: 10