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

Dataset: The Pile

Neuron 1337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1071889 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8338. Min Act: -0.0000

Data Index: 207028 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8236. Min Act: -0.0000

Data Index: 693656 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1293553 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7584. Min Act: -0.0000

Data Index: 942405 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1250395 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7047. Min Act: 0.0000

Data Index: 193913 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6950. Min Act: 0.0000

Data Index: 1616340 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6929. Min Act: -0.0000

Data Index: 402763 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7343. Min Act: 0.0000

Data Index: 766889 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6727. Min Act: 0.0000

Data Index: 228166 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6593. Min Act: 0.0000

Data Index: 379643 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1203293 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6321. Min Act: -0.0000

Data Index: 230223 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1616617 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6375. Min Act: -0.0000

Data Index: 657974 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1323225 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1749961 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5645. Min Act: 0.0000

Data Index: 156308 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1137730 (The Pile)

Max Activating Token Index: 465