Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.1982. Min Act: -0.0002

Data Index: 1370296 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.1837. Min Act: -0.0002

Data Index: 1419082 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.1080. Min Act: -0.0002

Data Index: 1625533 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0251. Min Act: -0.0002

Data Index: 1635911 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0210. Min Act: -0.0002

Data Index: 1560553 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0255. Min Act: -0.0002

Data Index: 1560968 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9992. Min Act: -0.0002

Data Index: 1361989 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9825. Min Act: -0.0002

Data Index: 1540899 (Python Code)

Max Activating Token Index: 276

Text #8

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9859. Min Act: -0.0002

Data Index: 1424387 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9830. Min Act: -0.0002

Data Index: 1488264 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9770. Min Act: -0.0002

Data Index: 1474412 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9819. Min Act: -0.0002

Data Index: 1439424 (Python Code)

Max Activating Token Index: 840

Text #12

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9605. Min Act: -0.0002

Data Index: 1624540 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9567. Min Act: -0.0002

Data Index: 1491626 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9521. Min Act: -0.0002

Data Index: 1571058 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9535. Min Act: -0.0002

Data Index: 1551980 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9549. Min Act: -0.0002

Data Index: 1377127 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9613. Min Act: -0.0002

Data Index: 1377773 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9259. Min Act: -0.0002

Data Index: 1510400 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9348. Min Act: -0.0002

Data Index: 1368184 (Python Code)

Max Activating Token Index: 462