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

Dataset: The Pile

Neuron 2800 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: 0.5047. Min Range: -0.5047

Max Act: 0.5047. Min Act: -0.0000

Data Index: 865879 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4856. Min Act: -0.0000

Data Index: 955438 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1913727 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1460761 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1895444 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3460. Min Act: -0.0000

Data Index: 592300 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3556. Min Act: -0.0000

Data Index: 953734 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3488. Min Act: -0.0000

Data Index: 122112 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1962591 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3641. Min Act: -0.0000

Data Index: 3577 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1780559 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3569. Min Act: -0.0000

Data Index: 72225 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3270. Min Act: -0.0000

Data Index: 749020 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3355. Min Act: -0.0000

Data Index: 173387 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1564608 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.2961. Min Act: -0.0000

Data Index: 715755 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3211. Min Act: -0.0000

Data Index: 449042 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3080. Min Act: -0.0000

Data Index: 939831 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1211564 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3504. Min Act: -0.0000

Data Index: 624952 (The Pile)

Max Activating Token Index: 94