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

Dataset: The Pile

Neuron 167 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: 0.6482. Min Range: -0.6482

Max Act: 0.6482. Min Act: -0.0000

Data Index: 479229 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1782282 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5572. Min Act: -0.0000

Data Index: 251971 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1918063 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5496. Min Act: -0.0000

Data Index: 413277 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5909. Min Act: -0.0000

Data Index: 389617 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1262298 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5261. Min Act: -0.0000

Data Index: 522804 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1359851 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.6165. Min Act: -0.0000

Data Index: 892947 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4845. Min Act: -0.0000

Data Index: 537736 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5334. Min Act: -0.0000

Data Index: 581378 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5256. Min Act: -0.0000

Data Index: 788540 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1490209 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4766. Min Act: -0.0000

Data Index: 599572 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1442158 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1888790 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5107. Min Act: -0.0000

Data Index: 636055 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1825922 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.6482. Min Range: -0.6482

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1225496 (The Pile)

Max Activating Token Index: 871