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

Dataset: The Pile

Neuron 4852 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: 3.7006. Min Range: -3.7006

Max Act: 3.7003. Min Act: -0.0000

Data Index: 1851688 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.6766. Min Act: -0.0000

Data Index: 930589 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3500. Min Act: -0.0000

Data Index: 77419 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3890. Min Act: -0.0000

Data Index: 118588 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.5134. Min Act: -0.0000

Data Index: 717320 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.7006. Min Act: -0.0000

Data Index: 1524296 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3155. Min Act: -0.0000

Data Index: 338279 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3134. Min Act: -0.0000

Data Index: 1654002 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.4487. Min Act: -0.0000

Data Index: 457191 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3823. Min Act: -0.0000

Data Index: 362634 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.4120. Min Act: -0.0000

Data Index: 663642 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.4775. Min Act: -0.0000

Data Index: 251831 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.1846. Min Act: -0.0000

Data Index: 717114 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3296. Min Act: -0.0000

Data Index: 1192574 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.2602. Min Act: -0.0000

Data Index: 1258002 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.0889. Min Act: -0.0000

Data Index: 1436779 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.4178. Min Act: -0.0000

Data Index: 754781 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.2542. Min Act: -0.0000

Data Index: 1155961 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.3886. Min Act: -0.0000

Data Index: 1720897 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 3.7006. Min Range: -3.7006

Max Act: 3.4072. Min Act: -0.0000

Data Index: 1616636 (The Pile)

Max Activating Token Index: 233