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

Dataset: The Pile

Neuron 1861 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: 1.6317. Min Range: -1.6317

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1859727 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.3975. Min Act: -0.0000

Data Index: 1651326 (The Pile)

Max Activating Token Index: 445

Text #2

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.3381. Min Act: -0.0000

Data Index: 412362 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.3349. Min Act: -0.0000

Data Index: 347284 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1807616 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.3155. Min Act: -0.0000

Data Index: 1406886 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1724607 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1972. Min Act: -0.0000

Data Index: 360936 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1572525 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.2424. Min Act: -0.0000

Data Index: 891745 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1722. Min Act: -0.0000

Data Index: 362563 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1440385 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1366. Min Act: -0.0000

Data Index: 432554 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.2933. Min Act: -0.0000

Data Index: 506505 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1480775 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1303. Min Act: -0.0000

Data Index: 555855 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1328. Min Act: -0.0000

Data Index: 53024 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1070167 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.0746. Min Act: -0.0000

Data Index: 637852 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.6317. Min Range: -1.6317

Max Act: 1.0734. Min Act: -0.0000

Data Index: 130422 (The Pile)

Max Activating Token Index: 1008