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

Dataset: The Pile

Neuron 4363 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: 5.3266. Min Range: -5.3266

Max Act: 4.7544. Min Act: -0.0000

Data Index: 1324883 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 5.3266. Min Range: -5.3266

Max Act: 5.3266. Min Act: -0.0000

Data Index: 1507768 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.6445. Min Act: -0.0000

Data Index: 634898 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.3520. Min Act: -0.0000

Data Index: 394040 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.3482. Min Act: -0.0000

Data Index: 84801 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.4632. Min Act: -0.0000

Data Index: 1539381 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.5412. Min Act: -0.0000

Data Index: 8046 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1245. Min Act: -0.0000

Data Index: 1896279 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.3687. Min Act: -0.0000

Data Index: 2542 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1614. Min Act: -0.0000

Data Index: 1817097 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.9426. Min Act: -0.0000

Data Index: 1658620 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1069. Min Act: -0.0000

Data Index: 1147848 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.0705. Min Act: -0.0000

Data Index: 1027284 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.9238. Min Act: -0.0000

Data Index: 111621 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.7157. Min Act: -0.0000

Data Index: 937048 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.8771. Min Act: -0.0000

Data Index: 1587207 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1654. Min Act: -0.0000

Data Index: 324271 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1009. Min Act: -0.0000

Data Index: 646276 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.0642. Min Act: -0.0000

Data Index: 576308 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.8699. Min Act: -0.0000

Data Index: 324907 (The Pile)

Max Activating Token Index: 220