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

Dataset: The Pile

Neuron 2657 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: 1.0117. Min Range: -1.0117

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1273452 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8204. Min Act: -0.0000

Data Index: 131819 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7997. Min Act: -0.0000

Data Index: 431680 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1983853 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6514. Min Act: -0.0000

Data Index: 260478 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7329. Min Act: -0.0000

Data Index: 357059 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1590447 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1054653 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7285. Min Act: -0.0000

Data Index: 674994 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7687. Min Act: -0.0000

Data Index: 429631 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7297. Min Act: -0.0000

Data Index: 667818 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1751279 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6825. Min Act: -0.0000

Data Index: 249241 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6555. Min Act: -0.0000

Data Index: 207499 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6993. Min Act: -0.0000

Data Index: 834498 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6624. Min Act: -0.0000

Data Index: 400052 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6983. Min Act: -0.0000

Data Index: 822655 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1954477 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1013938 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1740779 (The Pile)

Max Activating Token Index: 621