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

Dataset: The Pile

Neuron 4919 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0000

Data Index: 30237 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0595. Min Act: -0.0000

Data Index: 666482 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0557. Min Act: 0.0000

Data Index: 581570 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1533521 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0510. Min Act: -0.0000

Data Index: 446126 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0510. Min Act: -0.0000

Data Index: 24784 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0504. Min Act: 0.0000

Data Index: 1153558 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0504. Min Act: -0.0000

Data Index: 88471 (The Pile)

Max Activating Token Index: 53

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1196047 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1374571 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0494. Min Act: -0.0000

Data Index: 38768 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0492. Min Act: 0.0000

Data Index: 1682009 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0473. Min Act: 0.0000

Data Index: 1522135 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0491. Min Act: -0.0000

Data Index: 983815 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0488. Min Act: -0.0000

Data Index: 624286 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1657833 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0489. Min Act: 0.0000

Data Index: 623333 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0485. Min Act: -0.0000

Data Index: 244068 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0485. Min Act: 0.0000

Data Index: 552836 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0482. Min Act: 0.0000

Data Index: 442471 (The Pile)

Max Activating Token Index: 53