Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1975. Min Act: -0.0000

Data Index: 245261 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1254660 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1656. Min Act: -0.0000

Data Index: 140504 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1518226 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1686. Min Act: -0.0000

Data Index: 596683 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1503809 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1818. Min Act: -0.0000

Data Index: 116821 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1681. Min Act: -0.0000

Data Index: 177279 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1184996 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1752. Min Act: -0.0000

Data Index: 558110 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1628. Min Act: -0.0000

Data Index: 953431 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1844792 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1654. Min Act: -0.0000

Data Index: 469723 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1112314 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1606. Min Act: -0.0000

Data Index: 737964 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1537. Min Act: -0.0000

Data Index: 736626 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1685. Min Act: -0.0000

Data Index: 701512 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1064810 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1857913 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1585113 (The Pile)

Max Activating Token Index: 228