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

Dataset: The Pile

Neuron 3852 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5780. Min Range: -3.5780

Max Act: 3.5780. Min Act: -0.0000

Data Index: 1936830 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.3598. Min Act: -0.0000

Data Index: 866057 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.5591. Min Act: -0.0000

Data Index: 1222282 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.1309. Min Act: -0.0000

Data Index: 60343 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.2510. Min Act: -0.0000

Data Index: 822718 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.3101. Min Act: -0.0000

Data Index: 1686545 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.9516. Min Act: -0.0000

Data Index: 561357 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 3.5780. Min Range: -3.5780

Max Act: 2.1243. Min Act: -0.0000

Data Index: 285731 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.9037. Min Act: -0.0000

Data Index: 456101 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.8603. Min Act: -0.0000

Data Index: 154716 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.7074. Min Act: -0.0000

Data Index: 1571406 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1069881 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1881827 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1792940 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1022396 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.7361. Min Act: -0.0000

Data Index: 921988 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.7448. Min Act: -0.0000

Data Index: 678799 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.6783. Min Act: -0.0000

Data Index: 1204081 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.6672. Min Act: -0.0000

Data Index: 1020518 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 3.5780. Min Range: -3.5780

Max Act: 1.5046. Min Act: -0.0000

Data Index: 162412 (The Pile)

Max Activating Token Index: 933