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

Dataset: The Pile

Neuron 1455 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: 5.7685. Min Range: -5.7685

Max Act: 5.7685. Min Act: -0.0000

Data Index: 1136396 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.4822. Min Act: -0.0000

Data Index: 1633030 (The Pile)

Max Activating Token Index: 823

Text #2

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.0694. Min Act: -0.0000

Data Index: 593404 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.0598. Min Act: -0.0000

Data Index: 372109 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.0444. Min Act: -0.0000

Data Index: 1246459 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8439. Min Act: -0.0000

Data Index: 664495 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.0054. Min Act: -0.0000

Data Index: 1405164 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8942. Min Act: -0.0000

Data Index: 1719954 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8736. Min Act: -0.0000

Data Index: 985465 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8422. Min Act: -0.0000

Data Index: 1096034 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8329. Min Act: -0.0000

Data Index: 1204234 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.6456. Min Act: -0.0000

Data Index: 578473 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8013. Min Act: -0.0000

Data Index: 555155 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.4391. Min Act: -0.0000

Data Index: 853173 (The Pile)

Max Activating Token Index: 606

Text #14

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.4428. Min Act: -0.0000

Data Index: 897888 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.7417. Min Act: -0.0000

Data Index: 1342366 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.6774. Min Act: -0.0000

Data Index: 824003 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.5701. Min Act: -0.0000

Data Index: 1954329 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 5.7685. Min Range: -5.7685

Max Act: 5.0475. Min Act: -0.0000

Data Index: 172052 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 5.7685. Min Range: -5.7685

Max Act: 4.8224. Min Act: -0.0000

Data Index: 569216 (The Pile)

Max Activating Token Index: 477