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

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

Neuron 3304 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1488439 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1409692 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1429470 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1461403 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1455971 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1398738 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1597909 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1632830 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1534138 (Python Code)

Max Activating Token Index: 519

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1411842 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1593801 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1508118 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1552823 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1582069 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1524724 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1624552 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1609827 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1368917 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1569871 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1486751 (Python Code)

Max Activating Token Index: 91