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

Dataset: The Pile

Neuron 4699 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: 0.8434. Min Range: -0.8434

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1593395 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1343511 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7009. Min Act: -0.0000

Data Index: 916578 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1989168 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1794175 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5653. Min Act: -0.0000

Data Index: 404892 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1245819 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1472548 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1737079 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1078891 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5266. Min Act: -0.0000

Data Index: 882338 (The Pile)

Max Activating Token Index: 109

Text #11

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1594371 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5855. Min Act: 0.0000

Data Index: 857371 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1346145 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5380. Min Act: -0.0000

Data Index: 600303 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5576. Min Act: -0.0000

Data Index: 213190 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1899031 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1605009 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5232. Min Act: -0.0000

Data Index: 115983 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.4642. Min Act: -0.0000

Data Index: 7348 (The Pile)

Max Activating Token Index: 687