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

Dataset: The Pile

Neuron 2753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1976118 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1041528 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 95903 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 933845 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 545197 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1924135 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 905229 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1536051 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 497726 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 63218 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1594808 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1967603 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 1269638 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 713111 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 693711 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1641374 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 828763 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 315362 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 718385 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 1697373 (The Pile)

Max Activating Token Index: 96