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

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

Neuron 3733 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: 1.0648. Min Range: -1.0648

Max Act: 1.0648. Min Act: -0.0001

Data Index: 553682 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1628616 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1385628 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1548713 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1430952 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1455091 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8633. Min Act: -0.0001

Data Index: 777455 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8189. Min Act: -0.0001

Data Index: 1551566 (Python Code)

Max Activating Token Index: 327

Text #8

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8554. Min Act: -0.0000

Data Index: 597956 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1546357 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1585639 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8591. Min Act: -0.0001

Data Index: 1551989 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8222. Min Act: -0.0001

Data Index: 806190 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1455065 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8418. Min Act: -0.0001

Data Index: 1256748 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8401. Min Act: -0.0001

Data Index: 937704 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8281. Min Act: -0.0001

Data Index: 82890 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1650690 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1381792 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.8291. Min Act: -0.0001

Data Index: 268963 (C4 (Web Text))

Max Activating Token Index: 619