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

Dataset: The Pile

Neuron 4997 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1283110 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.7435. Min Act: -0.0000

Data Index: 403472 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6773. Min Act: -0.0000

Data Index: 640277 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6987. Min Act: -0.0000

Data Index: 914527 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6762. Min Act: -0.0000

Data Index: 382742 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.6223. Min Act: -0.0000

Data Index: 170744 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1181936 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5317. Min Act: -0.0000

Data Index: 322648 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4988. Min Act: -0.0000

Data Index: 39810 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.5002. Min Act: -0.0000

Data Index: 31455 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4730. Min Act: -0.0000

Data Index: 676133 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1120095 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1768292 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1423391 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4856. Min Act: -0.0000

Data Index: 980650 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1250743 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1762756 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4302. Min Act: -0.0000

Data Index: 566488 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1771425 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 0.7435. Min Range: -0.7435

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1808818 (The Pile)

Max Activating Token Index: 551