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

Dataset: The Pile

Neuron 3589 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: 3.7882. Min Range: -3.7882

Max Act: 3.7882. Min Act: -0.0000

Data Index: 1136563 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.7476. Min Act: -0.0000

Data Index: 1740380 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6408. Min Act: -0.0000

Data Index: 314170 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.3600. Min Act: -0.0000

Data Index: 1988473 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.2632. Min Act: -0.0000

Data Index: 1068581 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.2557. Min Act: -0.0000

Data Index: 775741 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1501256 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1811. Min Act: -0.0000

Data Index: 536151 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.9633. Min Act: -0.0000

Data Index: 1035699 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0985. Min Act: -0.0000

Data Index: 1697067 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0412. Min Act: -0.0000

Data Index: 756654 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0579. Min Act: -0.0000

Data Index: 995450 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0206. Min Act: -0.0000

Data Index: 625188 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0224. Min Act: -0.0000

Data Index: 791125 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0406. Min Act: -0.0000

Data Index: 817485 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.9751. Min Act: -0.0000

Data Index: 23038 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.8278. Min Act: -0.0000

Data Index: 1684190 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.9630. Min Act: -0.0000

Data Index: 415152 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.9314. Min Act: -0.0000

Data Index: 1551125 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.8691. Min Act: -0.0000

Data Index: 676374 (The Pile)

Max Activating Token Index: 246