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

Dataset: The Pile

Neuron 181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.5198. Min Act: -0.0000

Data Index: 682027 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1984. Min Act: -0.0000

Data Index: 528246 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2359. Min Act: -0.0000

Data Index: 773770 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1142969 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0659. Min Act: -0.0000

Data Index: 295265 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1549536 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2685. Min Act: -0.0000

Data Index: 200878 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1548. Min Act: -0.0000

Data Index: 68086 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1041757 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1855309 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0840. Min Act: -0.0000

Data Index: 48283 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1420056 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0008. Min Act: -0.0000

Data Index: 616799 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1700898 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1640942 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.5198. Min Range: -1.5198

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1526660 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1817145 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1569699 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.5198. Min Range: -1.5198

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1475782 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1760486 (The Pile)

Max Activating Token Index: 192