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

Dataset: The Pile

Neuron 4119 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.9579. Min Act: -0.0000

Data Index: 790061 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7165. Min Act: -0.0000

Data Index: 818904 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8201. Min Act: -0.0000

Data Index: 808659 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1437875 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1001064 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1949405 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1618044 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7551. Min Act: -0.0000

Data Index: 493756 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6747. Min Act: -0.0000

Data Index: 711651 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1637872 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7341. Min Act: -0.0000

Data Index: 113645 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6572. Min Act: -0.0000

Data Index: 87833 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1233679 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7482. Min Act: -0.0000

Data Index: 269179 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6753. Min Act: -0.0000

Data Index: 561105 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6846. Min Act: -0.0000

Data Index: 385458 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1546218 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6405. Min Act: -0.0000

Data Index: 385724 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6871. Min Act: -0.0000

Data Index: 161068 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1174418 (The Pile)

Max Activating Token Index: 815