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

Dataset: The Pile

Neuron 3727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.3002. Min Act: -0.0000

Data Index: 223683 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.3052. Min Act: -0.0000

Data Index: 930437 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1205314 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1208958 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2717. Min Act: -0.0000

Data Index: 300159 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1189961 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2561. Min Act: -0.0000

Data Index: 860795 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1661652 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1366763 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2447. Min Act: -0.0000

Data Index: 112567 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1209303 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2611. Min Act: -0.0000

Data Index: 179079 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1293344 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1136580 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1139817 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2327. Min Act: -0.0000

Data Index: 503313 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2218. Min Act: -0.0000

Data Index: 664960 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2537. Min Act: -0.0000

Data Index: 828946 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1341059 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.3052. Min Range: -0.3052

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1127354 (The Pile)

Max Activating Token Index: 901