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

Dataset: The Pile

Neuron 1990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1389197 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.6696. Min Act: -0.0000

Data Index: 1280421 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1038871 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1472524 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.6013. Min Act: -0.0000

Data Index: 1619674 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5543. Min Act: -0.0000

Data Index: 569479 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.4918. Min Act: -0.0000

Data Index: 1095646 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1577869 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5188. Min Act: -0.0000

Data Index: 240565 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.6567. Min Act: -0.0000

Data Index: 173720 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5902. Min Act: -0.0000

Data Index: 126538 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1817455 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5400. Min Act: -0.0000

Data Index: 187196 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.4411. Min Act: -0.0000

Data Index: 634035 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5665. Min Act: -0.0000

Data Index: 837684 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.4844. Min Act: -0.0000

Data Index: 250716 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1635923 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1260088 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.6034. Min Act: -0.0000

Data Index: 1864323 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 1.6696. Min Range: -1.6696

Max Act: 1.5169. Min Act: -0.0000

Data Index: 423049 (The Pile)

Max Activating Token Index: 134