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

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

Neuron 3577 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0273. Min Range: -2.0273

Max Act: 2.0273. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.8703. Min Act: -0.0000

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.9027. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.8473. Min Act: -0.0000

Data Index: 1487890 (Python Code)

Max Activating Token Index: 948

Text #4

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1549814 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1488542 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1481312 (Python Code)

Max Activating Token Index: 818

Text #7

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1476854 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1614908 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1454870 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4923. Min Act: -0.0000

Data Index: 1485147 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1570916 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1529372 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1522577 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4281. Min Act: -0.0000

Data Index: 1635798 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1612622 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4314. Min Act: -0.0000

Data Index: 1540412 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1462829 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1472248 (Python Code)

Max Activating Token Index: 848

Text #19

Max Range: 2.0273. Min Range: -2.0273

Max Act: 1.4293. Min Act: -0.0000

Data Index: 1424153 (Python Code)

Max Activating Token Index: 948