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

Dataset: The Pile

Neuron 3930 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0480. Min Range: -1.0480

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1989179 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9603. Min Act: -0.0000

Data Index: 21219 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9188. Min Act: -0.0000

Data Index: 586549 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9684. Min Act: -0.0000

Data Index: 1817097 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1436747 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9764. Min Act: -0.0000

Data Index: 385255 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1367633 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8553. Min Act: -0.0000

Data Index: 20358 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8775. Min Act: -0.0000

Data Index: 393485 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8373. Min Act: -0.0000

Data Index: 74096 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1050498 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8424. Min Act: -0.0000

Data Index: 560993 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8249. Min Act: -0.0000

Data Index: 445352 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1488824 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1521729 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1585769 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1087582 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7588. Min Act: -0.0000

Data Index: 483903 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7723. Min Act: -0.0000

Data Index: 209546 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7557. Min Act: -0.0000

Data Index: 475016 (The Pile)

Max Activating Token Index: 355