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

Dataset: The Pile

Neuron 4173 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1758989 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6834. Min Act: -0.0000

Data Index: 528492 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1407906 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.7209. Min Act: -0.0000

Data Index: 160316 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1506117 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.7190. Min Act: -0.0000

Data Index: 359555 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1259288 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1439686 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5536. Min Act: -0.0000

Data Index: 762086 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1401054 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1904051 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6083. Min Act: -0.0000

Data Index: 394449 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1974395 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1832403 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1488063 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5551. Min Act: -0.0000

Data Index: 812720 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5475. Min Act: -0.0000

Data Index: 611797 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5745. Min Act: -0.0000

Data Index: 894692 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1927791 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4965. Min Act: -0.0000

Data Index: 425116 (The Pile)

Max Activating Token Index: 395