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

Dataset: The Pile

Neuron 3735 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: 0.9712. Min Range: -0.9712

Max Act: 0.9712. Min Act: -0.0000

Data Index: 460561 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1372757 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1763560 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.9121. Min Act: -0.0000

Data Index: 273300 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1943445 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8972. Min Act: 0.0000

Data Index: 345801 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1731565 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1423465 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1114047 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8408. Min Act: -0.0000

Data Index: 426729 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1263755 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7844. Min Act: -0.0000

Data Index: 104798 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1352602 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1851366 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1704761 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7530. Min Act: -0.0000

Data Index: 324871 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7116. Min Act: -0.0000

Data Index: 309732 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7567. Min Act: -0.0000

Data Index: 615135 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7535. Min Act: 0.0000

Data Index: 1461385 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7912. Min Act: -0.0000

Data Index: 412724 (The Pile)

Max Activating Token Index: 558