Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3808 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1322789 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.0845. Min Act: -0.0000

Data Index: 633136 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.1913. Min Range: -1.1913

Max Act: 1.0011. Min Act: -0.0000

Data Index: 649934 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1820055 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8722. Min Act: -0.0000

Data Index: 109359 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.9157. Min Act: -0.0000

Data Index: 240804 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1626159 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1932658 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1127222 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1850710 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1512679 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.9419. Min Act: -0.0000

Data Index: 949424 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1004818 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1681101 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1264616 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1557451 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.7965. Min Act: -0.0000

Data Index: 937217 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1984466 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1521869 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.1913. Min Range: -1.1913

Max Act: 0.8048. Min Act: -0.0000

Data Index: 508154 (The Pile)

Max Activating Token Index: 803