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

Dataset: The Pile

Neuron 1990 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1286115 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1315938 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1037771 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1645226 (The Pile)

Max Activating Token Index: 787

Text #4

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1970340 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1153. Min Act: -0.0000

Data Index: 993507 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1672. Min Act: -0.0000

Data Index: 804981 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0173. Min Act: -0.0000

Data Index: 319681 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0835. Min Act: 0.0000

Data Index: 854258 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0682. Min Act: -0.0000

Data Index: 556128 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1169482 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1697841 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 1.3741. Min Range: -1.3741

Max Act: 0.9778. Min Act: -0.0000

Data Index: 943584 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0127. Min Act: -0.0000

Data Index: 129622 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 1.3741. Min Range: -1.3741

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1213966 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.3741. Min Range: -1.3741

Max Act: 0.9633. Min Act: -0.0000

Data Index: 905882 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1918750 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0816. Min Act: -0.0000

Data Index: 278224 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1300881 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.0205. Min Act: -0.0000

Data Index: 180198 (The Pile)

Max Activating Token Index: 371