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

Dataset: The Pile

Neuron 1044 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: 0.8683. Min Range: -0.8683

Max Act: 0.8683. Min Act: -0.0000

Data Index: 266406 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1431680 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1700130 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1279503 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7550. Min Act: -0.0000

Data Index: 257007 (The Pile)

Max Activating Token Index: 156

Text #5

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8055. Min Act: -0.0000

Data Index: 588836 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1670331 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7108. Min Act: -0.0000

Data Index: 363084 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6856. Min Act: -0.0000

Data Index: 211657 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1965971 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1206723 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6387. Min Act: -0.0000

Data Index: 376323 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6666. Min Act: -0.0000

Data Index: 766218 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6267. Min Act: -0.0000

Data Index: 385040 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6772. Min Act: -0.0000

Data Index: 965772 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6201. Min Act: -0.0000

Data Index: 778443 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1957245 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1788253 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6277. Min Act: -0.0000

Data Index: 968685 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1886149 (The Pile)

Max Activating Token Index: 512