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

Dataset: The Pile

Neuron 5052 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: 0.7718. Min Range: -0.7718

Max Act: 0.7718. Min Act: -0.0000

Data Index: 124633 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6966. Min Act: -0.0000

Data Index: 934037 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6031. Min Act: -0.0000

Data Index: 825544 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1158482 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1085307 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1440683 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1809476 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1233797 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1276946 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6422. Min Act: -0.0000

Data Index: 167899 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1337262 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1696076 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1997458 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5658. Min Act: -0.0000

Data Index: 304171 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1961852 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5571. Min Act: -0.0000

Data Index: 974777 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5949. Min Act: -0.0000

Data Index: 666470 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1324043 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1468988 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1478901 (The Pile)

Max Activating Token Index: 981