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

Dataset: The Pile

Neuron 2284 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: 5.8364. Min Range: -5.8364

Max Act: 5.8364. Min Act: -0.0000

Data Index: 210740 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 5.8364. Min Range: -5.8364

Max Act: 5.1838. Min Act: -0.0000

Data Index: 1833880 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.9337. Min Act: -0.0000

Data Index: 913103 (The Pile)

Max Activating Token Index: 598

Text #3

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.9809. Min Act: -0.0000

Data Index: 1597321 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.6415. Min Act: -0.0000

Data Index: 151829 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 5.8364. Min Range: -5.8364

Max Act: 5.0754. Min Act: -0.0000

Data Index: 905164 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.4633. Min Act: -0.0000

Data Index: 338945 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.3117. Min Act: -0.0000

Data Index: 285537 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.5986. Min Act: -0.0000

Data Index: 266783 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.5657. Min Act: -0.0000

Data Index: 834366 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.4605. Min Act: -0.0000

Data Index: 149938 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.8857. Min Act: -0.0000

Data Index: 99770 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.7039. Min Act: -0.0000

Data Index: 1858806 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.8988. Min Act: -0.0000

Data Index: 1263514 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.2635. Min Act: -0.0000

Data Index: 1917431 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.2610. Min Act: -0.0000

Data Index: 1868656 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.2083. Min Act: -0.0000

Data Index: 940427 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.4007. Min Act: -0.0000

Data Index: 516913 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.3401. Min Act: -0.0000

Data Index: 687964 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 5.8364. Min Range: -5.8364

Max Act: 4.2665. Min Act: -0.0000

Data Index: 1758837 (The Pile)

Max Activating Token Index: 591