Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4891. Min Act: -0.0000

Data Index: 703034 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1986797 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4690. Min Act: -0.0000

Data Index: 193573 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4824. Min Act: -0.0000

Data Index: 176841 (The Pile)

Max Activating Token Index: 355

Text #4

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1123498 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1895123 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1345863 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3677. Min Act: -0.0000

Data Index: 874177 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1074220 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3991. Min Act: -0.0000

Data Index: 65891 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1145181 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3689. Min Act: -0.0000

Data Index: 950545 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3801. Min Act: -0.0000

Data Index: 2824 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1643139 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1184712 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3766. Min Act: -0.0000

Data Index: 936532 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1762502 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3708. Min Act: -0.0000

Data Index: 342797 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3729. Min Act: -0.0000

Data Index: 656804 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 0.4966. Min Range: -0.4966

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1129835 (The Pile)

Max Activating Token Index: 74