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

Dataset: Open Web Text

Neuron 1978 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: 6.3230. Min Range: -6.3230

Max Act: 6.3024. Min Act: -0.1700

Data Index: 6194973 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.3230. Min Act: -0.1700

Data Index: 5067751 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.2606. Min Act: -0.1700

Data Index: 275752 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.2254. Min Act: -0.1700

Data Index: 5347299 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.2345. Min Act: -0.1700

Data Index: 1706087 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.2242. Min Act: -0.1700

Data Index: 999989 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1909. Min Act: -0.1700

Data Index: 3475496 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1644. Min Act: -0.1700

Data Index: 3615391 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1816. Min Act: -0.1700

Data Index: 4654909 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1904. Min Act: -0.1700

Data Index: 7055500 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1963. Min Act: -0.1700

Data Index: 709991 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1875. Min Act: -0.1700

Data Index: 6782816 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1801. Min Act: -0.1700

Data Index: 2124074 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1449. Min Act: -0.1700

Data Index: 7151581 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1601. Min Act: -0.1700

Data Index: 1749906 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1562. Min Act: -0.1700

Data Index: 891583 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1579. Min Act: -0.1700

Data Index: 5022402 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1552. Min Act: -0.1700

Data Index: 3297994 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1131. Min Act: -0.1700

Data Index: 4462096 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 6.3230. Min Range: -6.3230

Max Act: 6.1166. Min Act: -0.1700

Data Index: 1895487 (Open Web Text)

Max Activating Token Index: 6