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

Dataset: The Pile

Neuron 4008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1647709 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1465117 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1284419 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5357. Min Act: -0.0000

Data Index: 822446 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4849. Min Act: -0.0000

Data Index: 873321 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1711356 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1120660 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4806. Min Act: -0.0000

Data Index: 338431 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4588. Min Act: -0.0000

Data Index: 495125 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1042262 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1836909 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4545. Min Act: -0.0000

Data Index: 63987 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1484533 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4283. Min Act: -0.0000

Data Index: 741699 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4164. Min Act: -0.0000

Data Index: 125774 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1604745 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1869375 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3936. Min Act: -0.0000

Data Index: 621696 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1734449 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3960. Min Act: 0.0000

Data Index: 392628 (The Pile)

Max Activating Token Index: 67