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

Dataset: The Pile

Neuron 2949 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: 0.5012. Min Range: -0.5012

Max Act: 0.5012. Min Act: -0.0000

Data Index: 268755 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2875. Min Act: -0.0000

Data Index: 713029 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3086. Min Act: -0.0000

Data Index: 458733 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3228. Min Act: -0.0000

Data Index: 809578 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2693. Min Act: -0.0000

Data Index: 536044 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1877043 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2629. Min Act: -0.0000

Data Index: 421552 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2633. Min Act: -0.0000

Data Index: 938886 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2671. Min Act: -0.0000

Data Index: 99483 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1070487 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1957521 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2608. Min Act: -0.0000

Data Index: 913326 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2326. Min Act: -0.0000

Data Index: 672806 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2483. Min Act: -0.0000

Data Index: 986577 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2364. Min Act: -0.0000

Data Index: 163093 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2192. Min Act: -0.0000

Data Index: 133023 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1534663 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2444. Min Act: -0.0000

Data Index: 532797 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2366. Min Act: -0.0000

Data Index: 517955 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.2411. Min Act: -0.0000

Data Index: 668605 (The Pile)

Max Activating Token Index: 797