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

Dataset: The Pile

Neuron 4068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3284. Min Range: -5.3284

Max Act: 5.3284. Min Act: -0.0000

Data Index: 1533345 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 5.3284. Min Range: -5.3284

Max Act: 5.0788. Min Act: -0.0000

Data Index: 1333112 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.7277. Min Act: -0.0000

Data Index: 1893420 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 5.3284. Min Range: -5.3284

Max Act: 5.1999. Min Act: -0.0000

Data Index: 992663 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 5.3284. Min Range: -5.3284

Max Act: 5.0080. Min Act: -0.0000

Data Index: 142764 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.6080. Min Act: -0.0000

Data Index: 1627370 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.8909. Min Act: -0.0000

Data Index: 998214 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.6543. Min Act: -0.0000

Data Index: 935733 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.2951. Min Act: -0.0000

Data Index: 1625136 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.4089. Min Act: -0.0000

Data Index: 1964658 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.5343. Min Act: -0.0000

Data Index: 330501 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.5199. Min Act: -0.0000

Data Index: 1959615 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.3114. Min Act: -0.0000

Data Index: 1323726 (The Pile)

Max Activating Token Index: 769

Text #13

Max Range: 5.3284. Min Range: -5.3284

Max Act: 3.7600. Min Act: -0.0000

Data Index: 792627 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.2853. Min Act: -0.0000

Data Index: 1564179 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.6753. Min Act: -0.0000

Data Index: 1953367 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.3479. Min Act: -0.0000

Data Index: 728099 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.1298. Min Act: -0.0000

Data Index: 559628 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 5.3284. Min Range: -5.3284

Max Act: 3.9539. Min Act: -0.0000

Data Index: 1286978 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 5.3284. Min Range: -5.3284

Max Act: 4.1016. Min Act: -0.0000

Data Index: 497780 (The Pile)

Max Activating Token Index: 127