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

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

Neuron 3832 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: 0.0956. Min Range: -0.0956

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1653056 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1372890 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1381100 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1583836 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1426678 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1466776 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1628937 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1412684 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1476763 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1386769 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1577486 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1392340 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1485692 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1394098 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1558782 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1565373 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1650911 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1604140 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1428289 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.0956. Min Range: -0.0956

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1433805 (Python Code)

Max Activating Token Index: 2