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

Dataset: The Pile

Neuron 2260 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: 1.3780. Min Range: -1.3780

Max Act: 1.3780. Min Act: -0.0000

Data Index: 356875 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0841. Min Act: -0.0000

Data Index: 733892 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1368794 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1978595 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0290. Min Act: -0.0000

Data Index: 680776 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1937041 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1806174 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9590. Min Act: -0.0000

Data Index: 769634 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9603. Min Act: -0.0000

Data Index: 676825 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9792. Min Act: -0.0000

Data Index: 218222 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9503. Min Act: -0.0000

Data Index: 981901 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1618668 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8991. Min Act: -0.0000

Data Index: 215315 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1315373 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8887. Min Act: -0.0000

Data Index: 710061 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9743. Min Act: -0.0000

Data Index: 597601 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9440. Min Act: -0.0000

Data Index: 858427 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9646. Min Act: -0.0000

Data Index: 232285 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8387. Min Act: -0.0000

Data Index: 77800 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9817. Min Act: -0.0000

Data Index: 847875 (The Pile)

Max Activating Token Index: 893