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

Dataset: The Pile

Neuron 5006 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4415. Min Act: -0.0000

Data Index: 18746 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3889. Min Act: -0.0000

Data Index: 356047 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1801918 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4182. Min Act: -0.0000

Data Index: 166354 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4174. Min Act: -0.0000

Data Index: 12050 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1338304 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1009805 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1606579 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3914. Min Act: -0.0000

Data Index: 556239 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1262908 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3964. Min Act: -0.0000

Data Index: 930420 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1591879 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3983. Min Act: -0.0000

Data Index: 528898 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3719. Min Act: -0.0000

Data Index: 507872 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1565980 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1592813 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3657. Min Act: -0.0000

Data Index: 985799 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3729. Min Act: -0.0000

Data Index: 397966 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1750005 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.4460. Min Range: -0.4460

Max Act: 0.3631. Min Act: -0.0000

Data Index: 560264 (The Pile)

Max Activating Token Index: 201