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

Dataset: The Pile

Neuron 907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4989. Min Act: 0.0000

Data Index: 139801 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4991. Min Act: -0.0000

Data Index: 368614 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4404. Min Act: -0.0000

Data Index: 975815 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4225. Min Act: 0.0000

Data Index: 986139 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4180. Min Act: 0.0000

Data Index: 1827072 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1967717 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4051. Min Act: 0.0000

Data Index: 1502120 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1918101 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1452860 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4026. Min Act: -0.0000

Data Index: 611452 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1063015 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1054319 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1705778 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3962. Min Act: -0.0000

Data Index: 597103 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3828. Min Act: -0.0000

Data Index: 178922 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3704. Min Act: -0.0000

Data Index: 172962 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1377138 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1129649 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1093877 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3788. Min Act: 0.0000

Data Index: 1135956 (The Pile)

Max Activating Token Index: 813