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

Dataset: The Pile

Neuron 3608 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: 0.4767. Min Range: -0.4767

Max Act: 0.4597. Min Act: -0.0000

Data Index: 811340 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4274. Min Act: -0.0000

Data Index: 31646 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4767. Min Act: -0.0000

Data Index: 817197 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1656419 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.4393. Min Act: -0.0000

Data Index: 251721 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3643. Min Act: -0.0000

Data Index: 758217 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3820. Min Act: -0.0000

Data Index: 10548 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1484119 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3452. Min Act: -0.0000

Data Index: 415182 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3933. Min Act: -0.0000

Data Index: 369388 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3778. Min Act: -0.0000

Data Index: 902238 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3407. Min Act: -0.0000

Data Index: 288479 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1507220 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3229. Min Act: -0.0000

Data Index: 363454 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1013691 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3402. Min Act: -0.0000

Data Index: 840906 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3378. Min Act: -0.0000

Data Index: 513219 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3591. Min Act: -0.0000

Data Index: 569345 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1326824 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.4767. Min Range: -0.4767

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1401154 (The Pile)

Max Activating Token Index: 69