Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 215 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.4136. Min Act: -0.0000

Data Index: 520803 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.1559. Min Act: -0.0000

Data Index: 1399700 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.1899. Min Act: -0.0000

Data Index: 40518 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 3.4136. Min Range: -3.4136

Max Act: 3.1568. Min Act: -0.0000

Data Index: 1348069 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.9834. Min Act: -0.0000

Data Index: 1575345 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.9867. Min Act: -0.0000

Data Index: 1601996 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.9952. Min Act: -0.0000

Data Index: 1869008 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.8226. Min Act: -0.0000

Data Index: 1059306 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.9276. Min Act: -0.0000

Data Index: 684330 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.5867. Min Act: -0.0000

Data Index: 1799761 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1406100 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.7024. Min Act: -0.0000

Data Index: 1498132 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.6420. Min Act: -0.0000

Data Index: 60218 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1942525 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.7521. Min Act: -0.0000

Data Index: 1745797 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.6025. Min Act: -0.0000

Data Index: 737060 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.4691. Min Act: -0.0000

Data Index: 864326 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.4776. Min Act: -0.0000

Data Index: 1440334 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.7262. Min Act: -0.0000

Data Index: 1570865 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 3.4136. Min Range: -3.4136

Max Act: 2.3260. Min Act: -0.0000

Data Index: 1951311 (The Pile)

Max Activating Token Index: 640