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

Dataset: The Pile

Neuron 4628 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: 0.2537. Min Range: -0.2537

Max Act: 0.2537. Min Act: -0.0000

Data Index: 634112 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1794220 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2194. Min Act: -0.0000

Data Index: 855044 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1432697 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2097. Min Act: -0.0000

Data Index: 101336 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2013. Min Act: -0.0000

Data Index: 449433 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1912. Min Act: -0.0000

Data Index: 433577 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1947. Min Act: -0.0000

Data Index: 381652 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1500718 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1854. Min Act: -0.0000

Data Index: 907816 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1815. Min Act: -0.0000

Data Index: 101321 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1457156 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1514927 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1069257 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1757224 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1438632 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1313554 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1803. Min Act: -0.0000

Data Index: 676826 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1855. Min Act: -0.0000

Data Index: 223945 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1721. Min Act: -0.0000

Data Index: 864974 (The Pile)

Max Activating Token Index: 334