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

Dataset: The Pile

Neuron 2674 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: 0.4157. Min Range: -0.4157

Max Act: 0.4157. Min Act: -0.0000

Data Index: 720857 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1848428 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3054. Min Act: -0.0000

Data Index: 317902 (The Pile)

Max Activating Token Index: 991

Text #3

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2901. Min Act: -0.0000

Data Index: 942611 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1382054 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2647. Min Act: 0.0000

Data Index: 1062506 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1723245 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2777. Min Act: -0.0000

Data Index: 934864 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1419009 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1612694 (The Pile)

Max Activating Token Index: 716

Text #10

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2472. Min Act: -0.0000

Data Index: 190051 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2519. Min Act: -0.0000

Data Index: 894985 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1216563 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1265160 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1387248 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2405. Min Act: -0.0000

Data Index: 88841 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2271. Min Act: -0.0000

Data Index: 276425 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2329. Min Act: -0.0000

Data Index: 185450 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2490. Min Act: 0.0000

Data Index: 1772712 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.2259. Min Act: 0.0000

Data Index: 524742 (The Pile)

Max Activating Token Index: 327