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

Dataset: The Pile

Neuron 396 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.5866. Min Act: 0.0000

Data Index: 1269061 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4718. Min Act: -0.0000

Data Index: 15444 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1995446 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4229. Min Act: -0.0000

Data Index: 251195 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1998110 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1754472 (The Pile)

Max Activating Token Index: 17

Text #6

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4307. Min Act: -0.0000

Data Index: 689991 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4503. Min Act: -0.0000

Data Index: 809730 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4351. Min Act: 0.0000

Data Index: 229876 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1718608 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4153. Min Act: -0.0000

Data Index: 563884 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4075. Min Act: -0.0000

Data Index: 961375 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4227. Min Act: 0.0000

Data Index: 1387010 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4186. Min Act: 0.0000

Data Index: 1044365 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1011869 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1035507 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1523007 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.3842. Min Act: -0.0000

Data Index: 310995 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.3724. Min Act: -0.0000

Data Index: 107075 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 0.5866. Min Range: -0.5866

Max Act: 0.3716. Min Act: -0.0000

Data Index: 366112 (The Pile)

Max Activating Token Index: 17