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

Dataset: The Pile

Neuron 2826 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7721. Min Act: -0.0000

Data Index: 426953 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7511. Min Act: -0.0000

Data Index: 830180 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7815. Min Act: -0.0000

Data Index: 52579 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7469. Min Act: -0.0000

Data Index: 3183 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7610. Min Act: -0.0000

Data Index: 21338 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1214556 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1720200 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7411. Min Act: -0.0000

Data Index: 567960 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7301. Min Act: -0.0000

Data Index: 758953 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1437332 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6693. Min Act: -0.0000

Data Index: 600005 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1413585 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7015. Min Act: -0.0000

Data Index: 725590 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6932. Min Act: -0.0000

Data Index: 135229 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1480845 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1473870 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1473323 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6690. Min Act: -0.0000

Data Index: 561359 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1303546 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5950. Min Act: -0.0000

Data Index: 991611 (The Pile)

Max Activating Token Index: 395