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

Dataset: Open Web Text

Neuron 2948 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: 5.0877. Min Range: -5.0877

Max Act: 5.0823. Min Act: -0.1700

Data Index: 4529870 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0877. Min Act: -0.1700

Data Index: 3642909 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0770. Min Act: -0.1700

Data Index: 5684018 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0771. Min Act: -0.1700

Data Index: 7882913 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0579. Min Act: -0.1700

Data Index: 8707978 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0780. Min Act: -0.1700

Data Index: 6092378 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0597. Min Act: -0.1700

Data Index: 5971947 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0820. Min Act: -0.1700

Data Index: 4566735 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0295. Min Act: -0.1700

Data Index: 1568250 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 1481500 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0299. Min Act: -0.1700

Data Index: 4566671 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0332. Min Act: -0.1700

Data Index: 8670385 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0253. Min Act: -0.1700

Data Index: 2392069 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0048. Min Act: -0.1700

Data Index: 1358715 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 1362281 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 2652894 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 299201 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 1566925 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 322286 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.0877. Min Range: -5.0877

Max Act: 5.0173. Min Act: -0.1700

Data Index: 1867637 (Open Web Text)

Max Activating Token Index: 3