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

Dataset: The Pile

Neuron 4823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1962739 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1527218 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7594. Min Act: -0.0000

Data Index: 615676 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1052360 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7531. Min Act: -0.0000

Data Index: 982616 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7771. Min Act: -0.0000

Data Index: 687142 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1572716 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7327. Min Act: -0.0000

Data Index: 148881 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7344. Min Act: -0.0000

Data Index: 105511 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1948098 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1628912 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7036. Min Act: -0.0000

Data Index: 610085 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6879. Min Act: -0.0000

Data Index: 63866 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1832921 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1683443 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1596906 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6331. Min Act: -0.0000

Data Index: 245206 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1172887 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6347. Min Act: -0.0000

Data Index: 349373 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6505. Min Act: -0.0000

Data Index: 569142 (The Pile)

Max Activating Token Index: 124