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

Dataset: The Pile

Neuron 91 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1289157 (The Pile)

Max Activating Token Index: 986

Text #1

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6810. Min Act: -0.0000

Data Index: 715813 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1802999 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1316461 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6912. Min Act: -0.0000

Data Index: 354872 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1222135 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6307. Min Act: -0.0000

Data Index: 167196 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1398031 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6011. Min Act: -0.0000

Data Index: 80648 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1834105 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1540288 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1033709 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5828. Min Act: -0.0000

Data Index: 656713 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1802507 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5846. Min Act: -0.0000

Data Index: 104347 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1002054 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1198351 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5555. Min Act: -0.0000

Data Index: 976257 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1904111 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5880. Min Act: -0.0000

Data Index: 620918 (The Pile)

Max Activating Token Index: 907