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

Dataset: The Pile

Neuron 701 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: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1551308 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0650. Min Act: 0.0001

Data Index: 301750 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1804151 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0576. Min Act: 0.0000

Data Index: 1397959 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0562. Min Act: 0.0000

Data Index: 1877912 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0532. Min Act: 0.0001

Data Index: 1654798 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0496. Min Act: -0.0000

Data Index: 348998 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0493. Min Act: 0.0000

Data Index: 1636918 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0492. Min Act: 0.0001

Data Index: 1823601 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1322270 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1950206 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1290160 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0476. Min Act: 0.0000

Data Index: 1952812 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0475. Min Act: 0.0000

Data Index: 24212 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0468. Min Act: 0.0000

Data Index: 682976 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0467. Min Act: 0.0001

Data Index: 1099455 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0460. Min Act: 0.0000

Data Index: 1874603 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0457. Min Act: 0.0000

Data Index: 545131 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1598001 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0457. Min Act: 0.0000

Data Index: 1410977 (The Pile)

Max Activating Token Index: 1023