Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6231. Min Act: -0.0000

Data Index: 180808 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1752386 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6090. Min Act: -0.0000

Data Index: 258733 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6044. Min Act: -0.0000

Data Index: 577822 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1351720 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5823. Min Act: 0.0000

Data Index: 658114 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5742. Min Act: -0.0000

Data Index: 214671 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1857645 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5716. Min Act: 0.0001

Data Index: 1953082 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1229593 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5723. Min Act: -0.0000

Data Index: 719688 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5769. Min Act: -0.0000

Data Index: 405991 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5770. Min Act: -0.0000

Data Index: 738365 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1345404 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1660566 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1930694 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1957113 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1069906 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5561. Min Act: -0.0000

Data Index: 366709 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1491078 (The Pile)

Max Activating Token Index: 543