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

Dataset: Open Web Text

Neuron 1284 in Layer 0

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: 4.3736. Min Range: -4.3736

Max Act: 4.3736. Min Act: -0.1700

Data Index: 2043248 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.1727. Min Act: -0.1700

Data Index: 2299544 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.1427. Min Act: -0.1700

Data Index: 2500997 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.1537. Min Act: -0.1700

Data Index: 2890167 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.1558. Min Act: -0.1700

Data Index: 8488514 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.1198. Min Act: -0.1700

Data Index: 5281823 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.1055. Min Act: -0.1700

Data Index: 7709226 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0643. Min Act: -0.1700

Data Index: 1070035 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0710. Min Act: -0.1700

Data Index: 4249739 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0975. Min Act: -0.1700

Data Index: 3868414 (Open Web Text)

Max Activating Token Index: 745

Text #10

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0794. Min Act: -0.1700

Data Index: 513959 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0898. Min Act: -0.1700

Data Index: 7980170 (Open Web Text)

Max Activating Token Index: 662

Text #12

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0654. Min Act: -0.1700

Data Index: 7778503 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0710. Min Act: -0.1700

Data Index: 3541798 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0674. Min Act: -0.1700

Data Index: 3211361 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0822. Min Act: -0.1700

Data Index: 1223348 (Open Web Text)

Max Activating Token Index: 717

Text #16

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0672. Min Act: -0.1700

Data Index: 7766371 (Open Web Text)

Max Activating Token Index: 673

Text #17

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0835. Min Act: -0.1700

Data Index: 1552548 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0807. Min Act: -0.1700

Data Index: 4762192 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.0640. Min Act: -0.1700

Data Index: 2485316 (Open Web Text)

Max Activating Token Index: 651