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

Dataset: The Pile

Neuron 3714 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: 0.8911. Min Range: -0.8911

Max Act: 0.8428. Min Act: -0.0000

Data Index: 441180 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.8911. Min Act: -0.0000

Data Index: 872424 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1307706 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1773340 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1185416 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1769842 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.7030. Min Act: -0.0000

Data Index: 693740 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1876091 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6806. Min Act: -0.0000

Data Index: 603713 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1832508 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6610. Min Act: -0.0000

Data Index: 769 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1584305 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6349. Min Act: -0.0000

Data Index: 103773 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6631. Min Act: -0.0000

Data Index: 979234 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1450198 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.5972. Min Act: -0.0000

Data Index: 57921 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6256. Min Act: -0.0000

Data Index: 846233 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6865. Min Act: -0.0000

Data Index: 378041 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6934. Min Act: -0.0000

Data Index: 599082 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 0.8911. Min Range: -0.8911

Max Act: 0.6614. Min Act: -0.0000

Data Index: 460009 (The Pile)

Max Activating Token Index: 967