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

Dataset: The Pile

Neuron 1760 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7571. Min Act: -0.0000

Data Index: 468932 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7107. Min Act: -0.0000

Data Index: 425918 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1853325 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5979. Min Act: -0.0000

Data Index: 264783 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5989. Min Act: -0.0000

Data Index: 848890 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1814478 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1397618 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5729. Min Act: -0.0000

Data Index: 694699 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5890. Min Act: -0.0000

Data Index: 77907 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1847165 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1573879 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6009. Min Act: -0.0000

Data Index: 909553 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1847470 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5079. Min Act: -0.0000

Data Index: 381809 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1919163 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5395. Min Act: -0.0000

Data Index: 674708 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1614858 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1574667 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1375814 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5231. Min Act: -0.0000

Data Index: 835860 (The Pile)

Max Activating Token Index: 412