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

Dataset: The Pile

Neuron 1509 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1641337 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1496446 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4055. Min Act: -0.0000

Data Index: 822174 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4320. Min Act: -0.0000

Data Index: 536570 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1991525 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4040. Min Act: -0.0000

Data Index: 239585 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1874666 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4045. Min Act: -0.0000

Data Index: 176941 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1156740 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3976. Min Act: -0.0000

Data Index: 669430 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1612757 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1516399 (The Pile)

Max Activating Token Index: 970

Text #12

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3682. Min Act: -0.0000

Data Index: 115343 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1786844 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1735072 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1540152 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3651. Min Act: -0.0000

Data Index: 632350 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3600. Min Act: -0.0000

Data Index: 47539 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1146611 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1229671 (The Pile)

Max Activating Token Index: 721