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

Dataset: The Pile

Neuron 1585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1161547 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.0624. Min Act: -0.0000

Data Index: 658376 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.1449. Min Act: -0.0000

Data Index: 697089 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.0285. Min Act: -0.0000

Data Index: 519955 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1220312 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1436060 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9439. Min Act: -0.0000

Data Index: 881850 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1652093 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.0078. Min Act: -0.0000

Data Index: 308444 (The Pile)

Max Activating Token Index: 462

Text #9

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9088. Min Act: -0.0000

Data Index: 32940 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1936928 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1414617 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 1.1449. Min Range: -1.1449

Max Act: 1.0177. Min Act: -0.0000

Data Index: 484678 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1719255 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.8903. Min Act: -0.0000

Data Index: 985515 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1470254 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1385748 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.8978. Min Act: -0.0000

Data Index: 91799 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9376. Min Act: -0.0000

Data Index: 733558 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 1.1449. Min Range: -1.1449

Max Act: 0.9063. Min Act: -0.0000

Data Index: 222993 (The Pile)

Max Activating Token Index: 404