Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1012 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6465. Min Range: -2.6465

Max Act: 2.6465. Min Act: -0.0000

Data Index: 880899 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 2.6465. Min Range: -2.6465

Max Act: 2.4607. Min Act: -0.0000

Data Index: 161828 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 2.6465. Min Range: -2.6465

Max Act: 2.4018. Min Act: -0.0000

Data Index: 95609 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 2.6465. Min Range: -2.6465

Max Act: 2.2287. Min Act: -0.0000

Data Index: 123305 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 2.6465. Min Range: -2.6465

Max Act: 2.1857. Min Act: -0.0000

Data Index: 88511 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 2.6465. Min Range: -2.6465

Max Act: 2.1453. Min Act: -0.0000

Data Index: 60907 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.9460. Min Act: -0.0000

Data Index: 744368 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.9091. Min Act: -0.0000

Data Index: 304032 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.8946. Min Act: -0.0000

Data Index: 485318 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.8224. Min Act: -0.0000

Data Index: 827885 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.7897. Min Act: -0.0000

Data Index: 323553 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.7812. Min Act: -0.0000

Data Index: 749610 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.6063. Min Act: -0.0000

Data Index: 1333640 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.6012. Min Act: -0.0000

Data Index: 50291 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.5866. Min Act: -0.0000

Data Index: 856095 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.4821. Min Act: -0.0000

Data Index: 1085347 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.6412. Min Act: -0.0000

Data Index: 771628 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.5491. Min Act: -0.0000

Data Index: 85790 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.5403. Min Act: -0.0000

Data Index: 698410 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.6465. Min Range: -2.6465

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1179304 (C4 (Web Text))

Max Activating Token Index: 858