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

Dataset: The Pile

Neuron 429 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: 0.9782. Min Range: -0.9782

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1989487 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0000

Data Index: 580477 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1834164 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1707376 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1759318 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1135528 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8040. Min Act: -0.0000

Data Index: 78986 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8178. Min Act: -0.0000

Data Index: 569142 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8226. Min Act: -0.0000

Data Index: 957754 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9622. Min Act: -0.0000

Data Index: 462261 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1874595 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8528. Min Act: -0.0000

Data Index: 547632 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7237. Min Act: -0.0000

Data Index: 52496 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1451741 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1419290 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7400. Min Act: -0.0000

Data Index: 379623 (The Pile)

Max Activating Token Index: 840

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1770913 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1563635 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7697. Min Act: -0.0000

Data Index: 400318 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1075041 (The Pile)

Max Activating Token Index: 252