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

Dataset: The Pile

Neuron 712 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5727. Min Act: -0.0000

Data Index: 431243 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5662. Min Act: -0.0000

Data Index: 531167 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5494. Min Act: -0.0000

Data Index: 992555 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1322436 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5501. Min Act: -0.0000

Data Index: 134928 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4802. Min Act: -0.0000

Data Index: 323899 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1948653 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1791243 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5173. Min Act: -0.0000

Data Index: 488200 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1451847 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1194682 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1612651 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1803539 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1782377 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1847124 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4417. Min Act: -0.0000

Data Index: 582067 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4505. Min Act: -0.0000

Data Index: 575259 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4891. Min Act: -0.0000

Data Index: 591847 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4500. Min Act: -0.0000

Data Index: 72423 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4636. Min Act: -0.0000

Data Index: 226761 (The Pile)

Max Activating Token Index: 30