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

Dataset: The Pile

Neuron 1477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.8817. Min Act: -0.0000

Data Index: 241539 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1044647 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.6579. Min Act: -0.0000

Data Index: 356852 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1516613 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1991625 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1043058 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5347. Min Act: -0.0000

Data Index: 806064 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4341. Min Act: -0.0000

Data Index: 157114 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.7372. Min Act: -0.0000

Data Index: 550046 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.6212. Min Act: -0.0000

Data Index: 1069030 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1648857 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4539. Min Act: -0.0000

Data Index: 113116 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1445961 (The Pile)

Max Activating Token Index: 384

Text #13

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1360287 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4836. Min Act: -0.0000

Data Index: 251808 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1987670 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4788. Min Act: -0.0000

Data Index: 349897 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.5586. Min Act: -0.0000

Data Index: 678584 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4570. Min Act: -0.0000

Data Index: 1165493 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 1.8817. Min Range: -1.8817

Max Act: 1.4689. Min Act: -0.0000

Data Index: 493273 (The Pile)

Max Activating Token Index: 185