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

Dataset: The Pile

Neuron 1257 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: 1.3980. Min Range: -1.3980

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1902128 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3980. Min Act: -0.0000

Data Index: 1526228 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1072649 (The Pile)

Max Activating Token Index: 843

Text #3

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1624444 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3424. Min Act: -0.0000

Data Index: 1187383 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1494331 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3156. Min Act: -0.0000

Data Index: 726080 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1383. Min Act: -0.0000

Data Index: 937491 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1229983 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3711. Min Act: -0.0000

Data Index: 385437 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2025. Min Act: -0.0000

Data Index: 322184 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1435681 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1579222 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3583. Min Act: -0.0000

Data Index: 679029 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1977. Min Act: -0.0000

Data Index: 638901 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.2779. Min Act: -0.0000

Data Index: 20744 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1659395 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.1153. Min Act: -0.0000

Data Index: 192884 (The Pile)

Max Activating Token Index: 32

Text #18

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.3193. Min Act: -0.0000

Data Index: 897179 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 1.3980. Min Range: -1.3980

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1465508 (The Pile)

Max Activating Token Index: 1006