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

Dataset: The Pile

Neuron 2432 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: 0.8071. Min Range: -0.8071

Max Act: 0.8042. Min Act: -0.0000

Data Index: 946135 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.8067. Min Act: -0.0000

Data Index: 740226 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1145201 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1892995 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6453. Min Act: -0.0000

Data Index: 485807 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6327. Min Act: -0.0000

Data Index: 881438 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1074073 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5958. Min Act: -0.0000

Data Index: 871757 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1885000 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1374888 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5789. Min Act: -0.0000

Data Index: 939520 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1232756 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5430. Min Act: -0.0000

Data Index: 732871 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5519. Min Act: -0.0000

Data Index: 75872 (The Pile)

Max Activating Token Index: 205

Text #14

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1125895 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5616. Min Act: -0.0000

Data Index: 864200 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5475. Min Act: -0.0000

Data Index: 98727 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1664164 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1038406 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5758. Min Act: -0.0000

Data Index: 673580 (The Pile)

Max Activating Token Index: 837