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

Dataset: The Pile

Neuron 3477 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: 0.2462. Min Range: -0.2462

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1529211 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1096941 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1852526 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2153. Min Act: -0.0000

Data Index: 88667 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2104. Min Act: -0.0001

Data Index: 82010 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1913. Min Act: -0.0000

Data Index: 852767 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1956. Min Act: -0.0000

Data Index: 114627 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1022809 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1955507 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1510024 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1822475 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1736. Min Act: -0.0000

Data Index: 989348 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1537108 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1390661 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1819. Min Act: -0.0000

Data Index: 561177 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1107911 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1141876 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1874. Min Act: -0.0000

Data Index: 785600 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1563157 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1859. Min Act: -0.0000

Data Index: 317550 (The Pile)

Max Activating Token Index: 99