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

Dataset: The Pile

Neuron 4786 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: 0.7069. Min Range: -0.7069

Max Act: 0.7069. Min Act: -0.0000

Data Index: 967145 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1770878 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.7028. Min Act: -0.0000

Data Index: 484191 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6652. Min Act: -0.0000

Data Index: 783012 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6163. Min Act: -0.0000

Data Index: 935597 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5721. Min Act: -0.0000

Data Index: 283122 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1615018 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1911836 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1234902 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1339949 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5097. Min Act: -0.0000

Data Index: 344577 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5059. Min Act: -0.0000

Data Index: 321340 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1916730 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1786140 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1382984 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5024. Min Act: -0.0000

Data Index: 871362 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4831. Min Act: -0.0000

Data Index: 233541 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4796. Min Act: -0.0000

Data Index: 785192 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4756. Min Act: -0.0000

Data Index: 55197 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4896. Min Act: -0.0000

Data Index: 65381 (The Pile)

Max Activating Token Index: 132