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

Dataset: The Pile

Neuron 1870 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: 1.7024. Min Range: -1.7024

Max Act: 1.6179. Min Act: -0.0000

Data Index: 653621 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1527658 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1248606 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.6918. Min Act: -0.0000

Data Index: 1074201 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1466117 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1355209 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5525. Min Act: -0.0000

Data Index: 51881 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5081. Min Act: -0.0000

Data Index: 159244 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5982. Min Act: -0.0000

Data Index: 757436 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.4502. Min Act: -0.0000

Data Index: 926550 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1174525 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.3063. Min Act: -0.0000

Data Index: 260832 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.3864. Min Act: -0.0000

Data Index: 667438 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1168314 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5882. Min Act: -0.0000

Data Index: 1085056 (The Pile)

Max Activating Token Index: 887

Text #15

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.4457. Min Act: -0.0000

Data Index: 1226093 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.4803. Min Act: -0.0000

Data Index: 337052 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.3598. Min Act: -0.0000

Data Index: 113702 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1679763 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 1.7024. Min Range: -1.7024

Max Act: 1.5034. Min Act: -0.0000

Data Index: 234989 (The Pile)

Max Activating Token Index: 653