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

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

Neuron 2099 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: 0.1313. Min Range: -0.1313

Max Act: 0.1313. Min Act: -0.0001

Data Index: 643292 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1473902 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1051. Min Act: -0.0000

Data Index: 439151 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1534457 (Python Code)

Max Activating Token Index: 103

Text #4

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1592646 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1140500 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1474520 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1450048 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0988. Min Act: -0.0001

Data Index: 891692 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1069463 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1402492 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1051274 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1533498 (Python Code)

Max Activating Token Index: 495

Text #13

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0895. Min Act: -0.0000

Data Index: 377090 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1519659 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1555449 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1648906 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0901. Min Act: -0.0001

Data Index: 253110 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1366496 (Python Code)

Max Activating Token Index: 638

Text #19

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1579116 (Python Code)

Max Activating Token Index: 810