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

Dataset: The Pile

Neuron 4329 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4938. Min Act: 0.0000

Data Index: 193993 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1048149 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1396737 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1236495 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1877210 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1370775 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3856. Min Act: 0.0000

Data Index: 949674 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3599. Min Act: -0.0000

Data Index: 612378 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3585. Min Act: 0.0000

Data Index: 1131311 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3214. Min Act: -0.0000

Data Index: 709474 (The Pile)

Max Activating Token Index: 402

Text #10

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1637995 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3355. Min Act: -0.0000

Data Index: 666960 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3222. Min Act: -0.0000

Data Index: 327719 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1201498 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1948927 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3528. Min Act: -0.0000

Data Index: 682255 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3308. Min Act: 0.0000

Data Index: 1424640 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3073. Min Act: 0.0000

Data Index: 368716 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3217. Min Act: -0.0000

Data Index: 993313 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1070563 (The Pile)

Max Activating Token Index: 304