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

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

Neuron 4159 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9015. Min Act: -0.0001

Data Index: 1635629 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1555974 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1372366 (Python Code)

Max Activating Token Index: 313

Text #3

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8602. Min Act: -0.0001

Data Index: 1439049 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8204. Min Act: -0.0001

Data Index: 1634591 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.9278. Min Act: -0.0001

Data Index: 1517505 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1361152 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8265. Min Act: -0.0001

Data Index: 1614052 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1572882 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8070. Min Act: -0.0001

Data Index: 1402772 (Python Code)

Max Activating Token Index: 91

Text #10

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1537716 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1565583 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1656050 (Python Code)

Max Activating Token Index: 616

Text #13

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8152. Min Act: -0.0001

Data Index: 1526460 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1529964 (Python Code)

Max Activating Token Index: 930

Text #15

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7340. Min Act: -0.0001

Data Index: 1412748 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1494110 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1572089 (Python Code)

Max Activating Token Index: 486

Text #18

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1388993 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7758. Min Act: -0.0001

Data Index: 1366941 (Python Code)

Max Activating Token Index: 541