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

Dataset: The Pile

Neuron 1503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1899714 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8592. Min Act: -0.0000

Data Index: 990836 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1372127 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.9033. Min Act: -0.0000

Data Index: 780634 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1726241 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1486816 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1855047 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7396. Min Act: -0.0000

Data Index: 279854 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7835. Min Act: -0.0000

Data Index: 469440 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1610170 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7865. Min Act: -0.0000

Data Index: 541527 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8053. Min Act: -0.0000

Data Index: 314488 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7704. Min Act: -0.0000

Data Index: 141490 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1498071 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1096494 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1590686 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6909. Min Act: -0.0000

Data Index: 298162 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7301. Min Act: -0.0000

Data Index: 170335 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7529. Min Act: -0.0000

Data Index: 667590 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7047. Min Act: -0.0000

Data Index: 312113 (The Pile)

Max Activating Token Index: 287