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

Dataset: The Pile

Neuron 4718 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: 0.9588. Min Range: -0.9588

Max Act: 0.8957. Min Act: -0.0000

Data Index: 157203 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.9588. Min Act: -0.0000

Data Index: 30030 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1306086 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7802. Min Act: -0.0001

Data Index: 63947 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7001. Min Act: -0.0000

Data Index: 868063 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1074299 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1428707 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1051954 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6839. Min Act: -0.0001

Data Index: 761930 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6624. Min Act: -0.0000

Data Index: 96150 (The Pile)

Max Activating Token Index: 761

Text #10

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7055. Min Act: -0.0000

Data Index: 163446 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1329749 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1694018 (The Pile)

Max Activating Token Index: 324

Text #13

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6823. Min Act: -0.0000

Data Index: 954041 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6891. Min Act: -0.0000

Data Index: 629579 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1394543 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1111478 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1305956 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.6648. Min Act: -0.0000

Data Index: 158742 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 0.9588. Min Range: -0.9588

Max Act: 0.5964. Min Act: -0.0000

Data Index: 428040 (The Pile)

Max Activating Token Index: 373