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

Dataset: The Pile

Neuron 5063 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1552119 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0610. Min Act: -0.0000

Data Index: 988291 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0585. Min Act: -0.0000

Data Index: 324893 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0582. Min Act: -0.0000

Data Index: 20377 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1141749 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0565. Min Act: -0.0000

Data Index: 67395 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0537. Min Act: -0.0000

Data Index: 175878 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1685095 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0503. Min Act: -0.0000

Data Index: 435628 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0502. Min Act: -0.0000

Data Index: 41556 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1786323 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0501. Min Act: -0.0000

Data Index: 921323 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0499. Min Act: -0.0000

Data Index: 327972 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1360905 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0495. Min Act: -0.0000

Data Index: 637373 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0492. Min Act: -0.0000

Data Index: 74059 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0488. Min Act: -0.0000

Data Index: 545709 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1347068 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1783299 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0474. Min Act: -0.0000

Data Index: 52850 (The Pile)

Max Activating Token Index: 1023