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

Dataset: The Pile

Neuron 4368 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1408. Min Act: -0.0000

Data Index: 640674 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1192. Min Act: -0.0000

Data Index: 862084 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1113009 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1514867 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0989. Min Act: -0.0000

Data Index: 961614 (The Pile)

Max Activating Token Index: 164

Text #5

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0825. Min Act: -0.0000

Data Index: 98286 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1019. Min Act: -0.0000

Data Index: 515867 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0900. Min Act: -0.0000

Data Index: 903106 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0896. Min Act: -0.0000

Data Index: 299100 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0822. Min Act: -0.0000

Data Index: 662268 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0941. Min Act: -0.0000

Data Index: 27107 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0908. Min Act: -0.0000

Data Index: 591354 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0866. Min Act: -0.0000

Data Index: 493448 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1427576 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0845. Min Act: -0.0000

Data Index: 203965 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1897870 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1868780 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1253086 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0808. Min Act: -0.0000

Data Index: 607450 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0815. Min Act: -0.0000

Data Index: 105328 (The Pile)

Max Activating Token Index: 1016