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

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

Neuron 1610 in Layer 0

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: 0.0926. Min Range: -0.0926

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1590726 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1402467 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1564246 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1534575 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1630869 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1402557 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1581776 (Python Code)

Max Activating Token Index: 88

Text #7

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1426807 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1608210 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1443501 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1435392 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1599939 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1415890 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1364063 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1388400 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1567747 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1487946 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1617065 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1500097 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1631278 (Python Code)

Max Activating Token Index: 63