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

Dataset: Open Web Text

Neuron 2506 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: 2.2339. Min Range: -2.2339

Max Act: 2.2339. Min Act: -0.1700

Data Index: 6949014 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1901. Min Act: -0.1698

Data Index: 3909657 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1717. Min Act: -0.1700

Data Index: 1517755 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1781. Min Act: -0.1700

Data Index: 1863836 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1867. Min Act: -0.1698

Data Index: 8045967 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1646. Min Act: -0.1700

Data Index: 8020816 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1640. Min Act: -0.1699

Data Index: 3966924 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1640. Min Act: -0.1699

Data Index: 2770518 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1452. Min Act: -0.1698

Data Index: 4812898 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1697

Data Index: 8743036 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1698

Data Index: 5981481 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1700

Data Index: 5956168 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1679

Data Index: 377781 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1700

Data Index: 3973287 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1694

Data Index: 4650619 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1700

Data Index: 4546311 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1350. Min Act: -0.1666

Data Index: 4033059 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1257. Min Act: -0.1684

Data Index: 6320572 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1231. Min Act: -0.1697

Data Index: 6154449 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.2339. Min Range: -2.2339

Max Act: 2.1075. Min Act: -0.1700

Data Index: 2107899 (Open Web Text)

Max Activating Token Index: 5