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

Dataset: The Pile

Neuron 2520 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: 0.0831. Min Range: -0.0831

Max Act: 0.0831. Min Act: -0.0000

Data Index: 165310 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1122791 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0742. Min Act: -0.0000

Data Index: 157605 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1989758 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1205512 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0567. Min Act: -0.0000

Data Index: 761898 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0530. Min Act: -0.0000

Data Index: 135990 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0558. Min Act: -0.0000

Data Index: 92992 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1918868 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0556. Min Act: -0.0000

Data Index: 276539 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0566. Min Act: -0.0000

Data Index: 998313 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0478. Min Act: -0.0000

Data Index: 448031 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1560024 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1788895 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0501. Min Act: -0.0000

Data Index: 557024 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0436. Min Act: -0.0000

Data Index: 377895 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1504695 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0459. Min Act: -0.0000

Data Index: 208729 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1318373 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1652118 (The Pile)

Max Activating Token Index: 347