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

Dataset: The Pile

Neuron 2830 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2412. Min Range: -1.2412

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1563214 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9942. Min Act: -0.0000

Data Index: 472024 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9081. Min Act: -0.0000

Data Index: 859589 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1929509 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1140118 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1266709 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.8406. Min Act: -0.0000

Data Index: 768688 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1624134 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1471403 (The Pile)

Max Activating Token Index: 826

Text #9

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1198551 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1974202 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7233. Min Act: -0.0000

Data Index: 408691 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1164921 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1896179 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6716. Min Act: -0.0000

Data Index: 569969 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7764. Min Act: -0.0000

Data Index: 353218 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.6708. Min Act: -0.0000

Data Index: 999411 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1829695 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7316. Min Act: -0.0000

Data Index: 434197 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.2412. Min Range: -1.2412

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1673119 (The Pile)

Max Activating Token Index: 278