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

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

Neuron 2347 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0360. Min Range: -1.0360

Max Act: 1.0360. Min Act: -0.0000

Data Index: 518488 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.9422. Min Act: -0.0000

Data Index: 85342 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7407. Min Act: -0.0000

Data Index: 978194 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7955. Min Act: -0.0000

Data Index: 501057 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.7072. Min Act: -0.0000

Data Index: 956798 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6918. Min Act: -0.0000

Data Index: 420255 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6973. Min Act: -0.0000

Data Index: 832237 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6931. Min Act: -0.0000

Data Index: 273085 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6596. Min Act: -0.0000

Data Index: 944020 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6593. Min Act: -0.0000

Data Index: 691694 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6293. Min Act: -0.0000

Data Index: 695766 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1276029 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6365. Min Act: -0.0000

Data Index: 176951 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1238578 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6679. Min Act: -0.0000

Data Index: 751385 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1417448 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6075. Min Act: -0.0000

Data Index: 767645 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1050016 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.6125. Min Act: -0.0000

Data Index: 825724 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.0360. Min Range: -1.0360

Max Act: 0.5532. Min Act: -0.0000

Data Index: 381925 (C4 (Web Text))

Max Activating Token Index: 647