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

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

Neuron 3416 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.2075. Min Act: -0.0000

Data Index: 1325555 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.1812. Min Act: -0.0000

Data Index: 58840 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0711. Min Act: -0.0000

Data Index: 961317 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9799. Min Act: -0.0000

Data Index: 72280 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0117. Min Act: -0.0000

Data Index: 255884 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9603. Min Act: -0.0000

Data Index: 901893 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.2075. Min Range: -1.2075

Max Act: 1.0291. Min Act: -0.0000

Data Index: 625200 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9118. Min Act: -0.0000

Data Index: 140749 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1301775 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9058. Min Act: -0.0000

Data Index: 108377 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9067. Min Act: -0.0000

Data Index: 376452 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9017. Min Act: -0.0000

Data Index: 253574 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1084662 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.8397. Min Act: -0.0000

Data Index: 659470 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1314745 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1307 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.8727. Min Act: -0.0000

Data Index: 193359 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9298. Min Act: -0.0000

Data Index: 615357 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1351651 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.2075. Min Range: -1.2075

Max Act: 0.8033. Min Act: -0.0000

Data Index: 682263 (C4 (Web Text))

Max Activating Token Index: 754