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

Dataset: The Pile

Neuron 808 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: 0.8888. Min Range: -0.8888

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1579580 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6629. Min Act: -0.0000

Data Index: 642190 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1425905 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6059. Min Act: -0.0000

Data Index: 186933 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5807. Min Act: -0.0000

Data Index: 90750 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6018. Min Act: -0.0000

Data Index: 517738 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1946253 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5912. Min Act: -0.0000

Data Index: 869167 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5758. Min Act: -0.0000

Data Index: 162180 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1260475 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5582. Min Act: -0.0000

Data Index: 736024 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5578. Min Act: -0.0000

Data Index: 348426 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5350. Min Act: -0.0000

Data Index: 251922 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5358. Min Act: -0.0000

Data Index: 460274 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1312200 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1855742 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5839. Min Act: -0.0000

Data Index: 646291 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1482170 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5511. Min Act: -0.0000

Data Index: 120381 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1999379 (The Pile)

Max Activating Token Index: 125