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

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

Neuron 4582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1651585 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1540522 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1564392 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1533444 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1506500 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0689. Min Act: -0.0000

Data Index: 721197 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1373823 (Python Code)

Max Activating Token Index: 560

Text #7

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1473210 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0593. Min Act: -0.0000

Data Index: 984614 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1593989 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1603238 (Python Code)

Max Activating Token Index: 209

Text #11

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1401050 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1573671 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1064436 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1520596 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1639009 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0518. Min Act: -0.0001

Data Index: 911328 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1222609 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0497. Min Act: -0.0000

Data Index: 911110 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.0494. Min Act: -0.0000

Data Index: 169596 (C4 (Web Text))

Max Activating Token Index: 259