Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2527. Min Act: -0.0000

Data Index: 840563 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2610. Min Act: -0.0000

Data Index: 792558 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2316. Min Act: -0.0000

Data Index: 590762 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1916893 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2229. Min Act: -0.0000

Data Index: 934827 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1925698 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1892620 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1369482 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2096. Min Act: -0.0000

Data Index: 177505 (The Pile)

Max Activating Token Index: 848

Text #9

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1306746 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1779361 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1845. Min Act: -0.0000

Data Index: 267417 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1888. Min Act: 0.0000

Data Index: 591982 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1518662 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1702021 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1952. Min Act: -0.0000

Data Index: 39624 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1130954 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1481734 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1690751 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1879. Min Act: -0.0000

Data Index: 856444 (The Pile)

Max Activating Token Index: 448