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

Dataset: The Pile

Neuron 2579 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: 0.5682. Min Range: -0.5682

Max Act: 0.5682. Min Act: -0.0000

Data Index: 943058 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.5140. Min Act: -0.0000

Data Index: 108577 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1186018 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1015532 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1502055 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3880. Min Act: -0.0000

Data Index: 278770 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1331361 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1763950 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4311. Min Act: -0.0000

Data Index: 761474 (The Pile)

Max Activating Token Index: 688

Text #9

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3760. Min Act: -0.0000

Data Index: 307255 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1401713 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3748. Min Act: -0.0000

Data Index: 317360 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.4172. Min Act: -0.0000

Data Index: 129469 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1829823 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3669. Min Act: -0.0000

Data Index: 298975 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1794084 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3725. Min Act: -0.0000

Data Index: 106220 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1340739 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3613. Min Act: -0.0000

Data Index: 506478 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.5682. Min Range: -0.5682

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1874993 (The Pile)

Max Activating Token Index: 295