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

Dataset: The Pile

Neuron 1366 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1622690 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1510307 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0975. Min Act: -0.0001

Data Index: 147915 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0931. Min Act: -0.0001

Data Index: 183257 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1594219 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0854. Min Act: -0.0001

Data Index: 495545 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0994. Min Act: -0.0001

Data Index: 107122 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1737605 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0902. Min Act: -0.0001

Data Index: 37800 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1095240 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0875. Min Act: -0.0001

Data Index: 736271 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1176036 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0839. Min Act: -0.0001

Data Index: 826186 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1591669 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1781385 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0826. Min Act: -0.0001

Data Index: 543549 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1838920 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0891. Min Act: -0.0001

Data Index: 779224 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1580240 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0790. Min Act: -0.0001

Data Index: 850235 (The Pile)

Max Activating Token Index: 716