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

Dataset: The Pile

Neuron 1712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1376736 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.5193. Min Act: -0.0000

Data Index: 658428 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.3433. Min Act: -0.0000

Data Index: 615641 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.1789. Min Act: -0.0000

Data Index: 967727 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.1194. Min Act: -0.0000

Data Index: 227065 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1127502 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1871993 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.0736. Min Act: -0.0000

Data Index: 591738 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.1053. Min Act: -0.0000

Data Index: 754939 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1888136 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 1.5193. Min Range: -1.5193

Max Act: 0.7550. Min Act: -0.0000

Data Index: 622952 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 1.5193. Min Range: -1.5193

Max Act: 0.8768. Min Act: -0.0000

Data Index: 180012 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.1100. Min Act: -0.0000

Data Index: 449306 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.5193. Min Range: -1.5193

Max Act: 0.9748. Min Act: -0.0000

Data Index: 582736 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.0094. Min Act: -0.0000

Data Index: 619246 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1671018 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.5193. Min Range: -1.5193

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1583075 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 1.5193. Min Range: -1.5193

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1350525 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 1.5193. Min Range: -1.5193

Max Act: 0.8250. Min Act: -0.0000

Data Index: 585661 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 1.5193. Min Range: -1.5193

Max Act: 0.9098. Min Act: -0.0000

Data Index: 876038 (The Pile)

Max Activating Token Index: 985