Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2216 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6352. Min Act: -0.0000

Data Index: 172655 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1959783 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1213571 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1911065 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5718. Min Act: -0.0000

Data Index: 159295 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1580866 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5624. Min Act: -0.0000

Data Index: 840992 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5664. Min Act: -0.0000

Data Index: 892782 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1947160 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1754423 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5626. Min Act: -0.0000

Data Index: 93678 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5271. Min Act: -0.0000

Data Index: 610105 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5967. Min Act: -0.0000

Data Index: 237463 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1566444 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5325. Min Act: -0.0000

Data Index: 45548 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5414. Min Act: -0.0000

Data Index: 156418 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1276204 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4857. Min Act: -0.0000

Data Index: 773526 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1089074 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5132. Min Act: -0.0000

Data Index: 675582 (The Pile)

Max Activating Token Index: 594