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

Dataset: The Pile

Neuron 3092 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: 0.6854. Min Range: -0.6854

Max Act: 0.6854. Min Act: -0.0000

Data Index: 930041 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1159085 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1913521 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1604197 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1796315 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1598938 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1685524 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4717. Min Act: -0.0000

Data Index: 822589 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4549. Min Act: -0.0000

Data Index: 293951 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4363. Min Act: -0.0000

Data Index: 274453 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1421073 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1259549 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4252. Min Act: -0.0000

Data Index: 449671 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4378. Min Act: -0.0000

Data Index: 27709 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1065427 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1820992 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1243063 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4196. Min Act: -0.0000

Data Index: 423420 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1530749 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.6854. Min Range: -0.6854

Max Act: 0.4118. Min Act: -0.0000

Data Index: 21365 (The Pile)

Max Activating Token Index: 582