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

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

Neuron 4684 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1454853 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1432572 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1460572 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1557390 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1451544 (Python Code)

Max Activating Token Index: 462

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1589278 (Python Code)

Max Activating Token Index: 474

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1484479 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1377002 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1408307 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1437979 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1447931 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1587957 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1007126 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1606083 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1447576 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1538502 (Python Code)

Max Activating Token Index: 849

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1552324 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1607893 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1556616 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1380582 (Python Code)

Max Activating Token Index: 252