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

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

Neuron 1356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1411035 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1628265 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1582415 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1602494 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1456944 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1493592 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1444281 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1369318 (Python Code)

Max Activating Token Index: 949

Text #8

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1515469 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1389729 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1415098 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1625628 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1467347 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1510233 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1637429 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1483333 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1456595 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1410477 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1498838 (Python Code)

Max Activating Token Index: 646

Text #19

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1420658 (Python Code)

Max Activating Token Index: 961