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

Dataset: The Pile

Neuron 1391 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.1110. Min Act: -0.0000

Data Index: 679480 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1557612 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1809528 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1757366 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0917. Min Act: -0.0000

Data Index: 991532 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0909. Min Act: -0.0000

Data Index: 212451 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1006699 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1201490 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0904. Min Act: -0.0000

Data Index: 407259 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0862. Min Act: -0.0000

Data Index: 151792 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0860. Min Act: -0.0000

Data Index: 994988 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0851. Min Act: -0.0000

Data Index: 136853 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0845. Min Act: -0.0000

Data Index: 32168 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1235688 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0840. Min Act: -0.0000

Data Index: 46445 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1478924 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1896620 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0816. Min Act: -0.0000

Data Index: 400316 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0812. Min Act: -0.0000

Data Index: 419273 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.1110. Min Range: -0.1110

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1473430 (The Pile)

Max Activating Token Index: 1003