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

Dataset: The Pile

Neuron 1608 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: 5.9035. Min Range: -5.9035

Max Act: 5.9035. Min Act: -0.0000

Data Index: 423603 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.7266. Min Act: -0.0000

Data Index: 774704 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.5070. Min Act: -0.0000

Data Index: 1980164 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.5405. Min Act: -0.0000

Data Index: 130828 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.6286. Min Act: -0.0000

Data Index: 1470324 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.5893. Min Act: -0.0000

Data Index: 1814557 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.3622. Min Act: -0.0000

Data Index: 1140858 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.0953. Min Act: -0.0000

Data Index: 1148983 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 5.9035. Min Range: -5.9035

Max Act: 4.8679. Min Act: -0.0000

Data Index: 1631605 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 5.9035. Min Range: -5.9035

Max Act: 4.9512. Min Act: -0.0000

Data Index: 1885618 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.2761. Min Act: -0.0000

Data Index: 1540750 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 5.9035. Min Range: -5.9035

Max Act: 4.9229. Min Act: -0.0000

Data Index: 1866588 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.0833. Min Act: -0.0000

Data Index: 1202862 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.0749. Min Act: -0.0000

Data Index: 1456071 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.0172. Min Act: -0.0000

Data Index: 114463 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.0420. Min Act: -0.0000

Data Index: 1414065 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.0021. Min Act: -0.0000

Data Index: 1016198 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 5.9035. Min Range: -5.9035

Max Act: 4.9713. Min Act: -0.0000

Data Index: 1364807 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.1603. Min Act: -0.0000

Data Index: 693131 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 5.9035. Min Range: -5.9035

Max Act: 5.1792. Min Act: -0.0000

Data Index: 1024838 (The Pile)

Max Activating Token Index: 882