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

Dataset: The Pile

Neuron 2461 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.7607. Min Act: -0.0000

Data Index: 207991 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.6958. Min Act: -0.0000

Data Index: 990019 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1753729 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1180852 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1682190 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5570. Min Act: -0.0000

Data Index: 683391 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5780. Min Act: -0.0000

Data Index: 239278 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1128380 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1286726 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1768855 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5596. Min Act: -0.0000

Data Index: 618362 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5055. Min Act: -0.0000

Data Index: 542334 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4937. Min Act: -0.0000

Data Index: 893510 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5432. Min Act: -0.0000

Data Index: 755560 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4909. Min Act: -0.0000

Data Index: 534035 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1448129 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1371724 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1910780 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1635638 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.7607. Min Range: -0.7607

Max Act: 0.4417. Min Act: -0.0000

Data Index: 133748 (The Pile)

Max Activating Token Index: 765