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

Dataset: The Pile

Neuron 750 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: 0.9189. Min Range: -0.9189

Max Act: 0.8721. Min Act: -0.0000

Data Index: 189646 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.9189. Min Act: -0.0000

Data Index: 765633 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1664918 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1300892 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7555. Min Act: -0.0000

Data Index: 911810 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7567. Min Act: -0.0000

Data Index: 866001 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6572. Min Act: -0.0000

Data Index: 906881 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6551. Min Act: -0.0000

Data Index: 44301 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.7330. Min Act: -0.0000

Data Index: 7318 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6304. Min Act: -0.0000

Data Index: 847222 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1595637 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1309881 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1460723 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.6027. Min Act: -0.0000

Data Index: 336967 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1563910 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1700160 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1281345 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5646. Min Act: -0.0000

Data Index: 907037 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1091470 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.9189. Min Range: -0.9189

Max Act: 0.5839. Min Act: -0.0000

Data Index: 429879 (The Pile)

Max Activating Token Index: 854