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

Dataset: The Pile

Neuron 165 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1796436 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2917. Min Act: -0.0000

Data Index: 917921 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1709609 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1037463 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1467233 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1161892 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1176352 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2376. Min Act: -0.0000

Data Index: 117415 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1688708 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1000855 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2617. Min Act: -0.0000

Data Index: 961496 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1530063 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1480092 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1354116 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1925629 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2123. Min Act: -0.0000

Data Index: 153644 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1373712 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1501745 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1475239 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2283. Min Act: -0.0000

Data Index: 245125 (The Pile)

Max Activating Token Index: 848