Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1751817 (The Pile)

Max Activating Token Index: 181

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1088. Min Act: -0.0000

Data Index: 569881 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1110. Min Act: -0.0000

Data Index: 684634 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1104. Min Act: -0.0000

Data Index: 635977 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1701496 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1672237 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0967. Min Act: -0.0000

Data Index: 88553 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0897. Min Act: -0.0000

Data Index: 197182 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0898. Min Act: -0.0000

Data Index: 151980 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0949. Min Act: -0.0000

Data Index: 842805 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1425315 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1350885 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0820. Min Act: -0.0000

Data Index: 953845 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1696435 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0756. Min Act: -0.0000

Data Index: 652973 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1326715 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1241554 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0876. Min Act: -0.0000

Data Index: 272941 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0835. Min Act: -0.0000

Data Index: 751049 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1827754 (The Pile)

Max Activating Token Index: 879